© 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. 119017
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their names

    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
    ntag
    -0.08
    agini
    -0.07
    hots
    -0.07
    venta
    -0.07
     ç¨
    -0.07
    çĶ²
    -0.07
    using
    -0.07
    ÙĪÙħÛĮ
    -0.07
    onces
    -0.07
    resi
    -0.07
    POSITIVE LOGITS
    essel
    0.07
     Vick
    0.06
    yer
    0.06
     Bon
    0.06
    997
    0.06
    ADR
    0.06
     cam
    0.05
    ippers
    0.05
    Boolean
    0.05
     Chu
    0.05
    Activations Density 0.008%

    No Known Activations