© 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. 125940
    Prev
    Next
    INDEX
    Explanations

    pronouns and expressions of personal experience or communication

    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
     defaultMessage
    -0.07
    kaar
    -0.07
    lut
    -0.07
    OrFail
    -0.07
    /flutter
    -0.07
    Handled
    -0.06
    arth
    -0.06
    appoint
    -0.06
    inos
    -0.06
    815
    -0.06
    POSITIVE LOGITS
    odge
    0.06
    igi
    0.06
     Virtual
    0.06
    pNet
    0.06
     Daily
    0.06
     Traffic
    0.06
     traffic
    0.06
     Platz
    0.06
     Jump
    0.06
     reve
    0.05
    Activations Density 0.000%

    No Known Activations