© 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. 15-LLAMASCOPE-RES-131K
    6. 26957
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities who possess or manage property or assets

    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
    endencies
    -0.07
    -speaking
    -0.07
    ulla
    -0.07
    are
    -0.07
     dozen
    -0.07
    ull
    -0.07
    ยà¸Ńà¸Ķ
    -0.07
    orgot
    -0.07
    wert
    -0.07
    eyn
    -0.07
    POSITIVE LOGITS
    /operator
    0.10
    /operators
    0.09
    hips
    0.09
    ship
    0.08
    -operator
    0.08
    hip
    0.07
    liness
    0.07
    chest
    0.07
    chaft
    0.07
    HIP
    0.07
    Activations Density 0.023%

    No Known Activations