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. 17-LLAMASCOPE-RES-32K
    6. 26582
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to contracts and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ìłģìľ¼ë¡ľ
    -0.15
    ewolf
    -0.15
    issant
    -0.15
    ynth
    -0.13
    raquo
    -0.13
    avras
    -0.13
    ethyst
    -0.13
    ilis
    -0.13
    andan
    -0.13
    plings
    -0.13
    POSITIVE LOGITS
    arter
    0.14
     erg
    0.14
    aura
    0.14
    á»ĵi
    0.13
    pond
    0.13
     Tube
    0.13
    ware
    0.13
     giz
    0.13
    erts
    0.13
    urance
    0.12
    Activations Density 0.546%

    No Known Activations