© 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. 129181
    Prev
    Next
    INDEX
    Explanations

    passive constructions and non-active expressions

    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
    Ïħγ
    -0.09
    wr
    -0.07
    dür
    -0.07
    ença
    -0.07
    ubb
    -0.06
    toa
    -0.06
    nova
    -0.06
     fieldValue
    -0.06
    åĶĩ
    -0.06
    logue
    -0.06
    POSITIVE LOGITS
    oji
    0.07
    _RB
    0.06
    .Formatter
    0.06
    mania
    0.06
    andler
    0.06
     Rotary
    0.06
    hton
    0.06
     Ful
    0.06
     Bols
    0.06
    ikes
    0.06
    Activations Density 0.133%

    No Known Activations