© 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. 71389
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership or possession

    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
    /ion
    -0.06
    uze
    -0.06
    opot
    -0.06
    ansen
    -0.06
    rena
    -0.06
    era
    -0.06
    imen
    -0.06
    ниÑĤ
    -0.05
     Spicer
    -0.05
    inki
    -0.05
    POSITIVE LOGITS
     Slut
    0.07
     this
    0.07
    HING
    0.07
    _fwd
    0.07
    Busy
    0.07
     nÃło
    0.07
     Busy
    0.06
     Burgess
    0.06
     UnsupportedOperationException
    0.06
    _except
    0.06
    Activations Density 0.001%

    No Known Activations