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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96231
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols in the text

    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
    808
    -0.07
    809
    -0.06
    anh
    -0.06
    orbit
    -0.06
    ammen
    -0.06
    FieldValue
    -0.06
    beck
    -0.06
    apters
    -0.05
    ing
    -0.05
    vu
    -0.05
    POSITIVE LOGITS
    agraph
    0.07
    ανδ
    0.07
    isphere
    0.07
    iteDatabase
    0.07
    DrawerToggle
    0.07
    sett
    0.07
    æ½®
    0.07
    rier
    0.07
    bedo
    0.07
    sert
    0.07
    Activations Density 0.053%

    No Known Activations