Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 9478
    Prev
    Next
    INDEX
    Explanations

    references to systems, mechanisms, or structures related to regulatory or operational frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to structured processes or systems involving components, connections, or mechanisms.

    oai_token-act-pair · gpt-4oTriggered by @tcai
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,and
    -0.14
    ,but
    -0.13
    /stretch
    -0.13
     bát
    -0.13
    ,â̦↵↵
    -0.13
     mastur
    -0.13
    rün
    -0.13
     prostitu
    -0.13
     CreateMap
    -0.12
    deme
    -0.12
    POSITIVE LOGITS
    &apos
    0.16
    Âłob
    0.14
    č
    0.13
     اÙĦرÙħزÙĬØ©
    0.13
    ÂŃi
    0.13
    ă
    0.13
      
    0.12
    utterstock
    0.12
     ¶
    0.12
     individually
    0.12
    Activations Density 93.521%

    No Known Activations