Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 118821
    Prev
    Next
    INDEX
    Explanations

    terms related to mold and its variations

    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
    asaki
    -0.07
    riba
    -0.07
     Pager
    -0.06
    ature
    -0.06
    ced
    -0.06
    TY
    -0.06
    à¸ľà¸¥
    -0.06
    _STRIP
    -0.06
    hta
    -0.06
    ordion
    -0.06
    POSITIVE LOGITS
    ovan
    0.09
    led
    0.08
    anh
    0.08
    gren
    0.08
    avian
    0.08
    sworth
    0.07
    mapper
    0.07
    avia
    0.07
    ings
    0.07
    ıa
    0.07
    Activations Density 0.003%

    No Known Activations