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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-LLAMASCOPE-RES-32K
    6. 7378
    Prev
    Next
    INDEX
    Explanations

    key terms related to regulations and requirements in government and law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eam
    -0.15
    bis
    -0.15
    spor
    -0.15
    asad
    -0.15
    yl
    -0.15
    Tiles
    -0.14
    ictim
    -0.14
    åĪĹ
    -0.14
    ιÏĥε
    -0.14
    issors
    -0.14
    POSITIVE LOGITS
    _UNS
    0.17
    omain
    0.14
    ạo
    0.14
    oze
    0.14
     failures
    0.14
    Ä±ÅŁÄ±k
    0.14
     Failure
    0.14
    ÑĢавилÑĮ
    0.14
    ingly
    0.14
    ä½ľ
    0.14
    Activations Density 0.371%

    No Known Activations