© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119177
    Prev
    Next
    INDEX
    Explanations

    phrases related to free access or entry

    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
    æ¨ĵ
    -0.07
    åī²
    -0.07
     Haut
    -0.06
    _MALLOC
    -0.06
    ug
    -0.06
    uto
    -0.06
    str
    -0.06
     dominance
    -0.06
    upy
    -0.06
    eref
    -0.06
    POSITIVE LOGITS
    Gratis
    0.07
     useClass
    0.07
    /free
    0.07
    Buffers
    0.07
    zes
    0.07
    rieve
    0.07
    bis
    0.07
    bie
    0.07
    (getClass
    0.06
     tạm
    0.06
    Activations Density 0.003%

    No Known Activations