© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96693
    Prev
    Next
    INDEX
    Explanations

    actions related to providing support or assistance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zwar
    -0.07
    orld
    -0.07
    242
    -0.06
    orks
    -0.06
    ãİ
    -0.06
    (æľ¨
    -0.06
    perms
    -0.06
    phin
    -0.06
     extent
    -0.06
    ãģĻãģİ
    -0.06
    POSITIVE LOGITS
     simultaneously
    0.07
    atta
    0.07
    ../../../
    0.06
    Īëĭ¤
    0.06
     correl
    0.06
    doch
    0.06
     embr
    0.06
    FUNC
    0.06
    idir
    0.06
     ALSO
    0.06
    Activations Density 0.036%

    No Known Activations