© 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. 15-LLAMASCOPE-RES-131K
    11. 1100
    Prev
    Next
    INDEX
    Explanations

    terms indicating signs or indicators of various conditions or situations

    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
    azu
    -0.06
     Academ
    -0.06
    fon
    -0.06
    ady
    -0.06
    estival
    -0.06
     Maison
    -0.06
     Huck
    -0.06
    Ùģات
    -0.06
    -Smith
    -0.06
    abet
    -0.06
    POSITIVE LOGITS
     of
    0.08
    strate
    0.07
    hoot
    0.07
    ahat
    0.07
    preferences
    0.06
    OfWork
    0.06
    HITE
    0.06
    ãĤ·ãĥ¼
    0.06
    /preferences
    0.06
     zda
    0.06
    Activations Density 0.012%

    No Known Activations