© 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. 17-LLAMASCOPE-RES-131K
    11. 83940
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations or predictions

    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
    antic
    -0.06
     itself
    -0.06
    monic
    -0.06
    rei
    -0.06
    iddy
    -0.06
    ovic
    -0.06
     already
    -0.06
    erto
    -0.05
    obbled
    -0.05
    icine
    -0.05
    POSITIVE LOGITS
    sar
    0.08
    æł·çļĦ
    0.07
    νο
    0.07
    ArgsConstructor
    0.07
    icode
    0.07
    RuntimeObject
    0.07
    /remove
    0.07
    _UNS
    0.07
    709
    0.07
    orate
    0.06
    Activations Density 0.005%

    No Known Activations