© 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. 61346
    Prev
    Next
    INDEX
    Explanations

    words related to scientific and technical concepts

    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
    ivia
    -0.08
     î¡
    -0.08
    fak
    -0.07
    essel
    -0.07
    ToBounds
    -0.07
    /XMLSchema
    -0.07
    elen
    -0.07
    ico
    -0.07
    Ìĥ
    -0.06
    ãĥ³ãĤ¯
    -0.06
    POSITIVE LOGITS
    axon
    0.07
    -dominated
    0.07
    /post
    0.07
    à¥įरध
    0.07
    /oct
    0.06
    ãĤ©
    0.06
    weg
    0.06
    /small
    0.06
    <small
    0.06
    /high
    0.06
    Activations Density 0.076%

    No Known Activations