© 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. 57507
    Prev
    Next
    INDEX
    Explanations

    references to bathrooms and garages in properties

    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
     mistr
    -0.06
    eil
    -0.06
    kan
    -0.06
    ongan
    -0.06
    ILED
    -0.06
     eros
    -0.06
    éij
    -0.06
    ìĨ
    -0.06
    her
    -0.06
    arily
    -0.06
    POSITIVE LOGITS
    sov
    0.07
    yte
    0.06
     Gür
    0.06
    SEQ
    0.06
    лик
    0.06
     åĭ
    0.06
    391
    0.06
    lick
    0.06
    sWith
    0.06
    acker
    0.06
    Activations Density 0.004%

    No Known Activations