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. 82920
    Prev
    Next
    INDEX
    Explanations

    references to relationships between individuals or groups

    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
    uyên
    -0.07
    amat
    -0.07
    andle
    -0.07
    ÄĽl
    -0.06
    isté
    -0.06
    orida
    -0.06
    alles
    -0.06
    uchi
    -0.06
    ame
    -0.06
    ocaly
    -0.06
    POSITIVE LOGITS
    /vendors
    0.07
    QObject
    0.07
    minus
    0.07
    们
    0.07
    /license
    0.07
    innen
    0.06
    ship
    0.06
     à¹Ĩ
    0.06
    .foundation
    0.06
     Olsen
    0.06
    Activations Density 0.030%

    No Known Activations