© 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. 118917
    Prev
    Next
    INDEX
    Explanations

    pronouns and expressions related to personal ownership and mental well-being

    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
    emales
    -0.07
     wheel
    -0.07
    iales
    -0.07
    apore
    -0.06
    wheel
    -0.06
    376
    -0.06
    plet
    -0.06
    .jd
    -0.06
    nice
    -0.06
    _wheel
    -0.06
    POSITIVE LOGITS
     options
    0.11
     Options
    0.10
    Options
    0.08
     own
    0.08
    options
    0.08
     OPTIONS
    0.07
    _options
    0.07
    ixo
    0.07
    -options
    0.07
     role
    0.07
    Activations Density 0.037%

    No Known Activations