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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61714
    Prev
    Next
    INDEX
    Explanations

    references to selections and collections of works or pieces, particularly in an artistic context

    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
    ÙĨÛĮÙĨ
    -0.07
    ãĤ¤ãĤ¹
    -0.07
    uš
    -0.07
    é¥
    -0.06
    dden
    -0.06
    hma
    -0.06
    _ZERO
    -0.06
    addon
    -0.06
    .handleSubmit
    -0.06
    eli
    -0.06
    POSITIVE LOGITS
    oris
    0.07
     lá»įc
    0.07
    TL
    0.07
    Bond
    0.07
    .getSelection
    0.07
    erc
    0.07
    Interior
    0.07
    LinkId
    0.07
    strup
    0.07
    items
    0.07
    Activations Density 0.009%

    No Known Activations