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. 13-LLAMASCOPE-RES-32K
    6. 26649
    Prev
    Next
    INDEX
    Explanations

    HTML elements and tags related to document structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eer
    -0.17
    addir
    -0.16
    odega
    -0.16
    hyth
    -0.14
    stroy
    -0.14
    åĬ¨çĶŁæĪIJ
    -0.14
    iegel
    -0.14
    stor
    -0.14
    atrix
    -0.14
    heimer
    -0.14
    POSITIVE LOGITS
    urn
    0.15
    elder
    0.15
    tere
    0.13
     TNT
    0.13
     Crosby
    0.13
    ourcem
    0.13
    fx
    0.13
    igers
    0.13
     Bundy
    0.13
    campo
    0.13
    Activations Density 0.002%

    No Known Activations