© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76998
    Prev
    Next
    INDEX
    Explanations

    detailed factual information about locations and statistics related to Manitoba

    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
    assa
    -0.07
     
    -0.06
    ÑĨ
    -0.06
     "
    -0.06
     Reserve
    -0.06
    asm
    -0.06
    ó
    -0.06
    ipsis
    -0.06
    znik
    -0.06
     trans
    -0.05
    POSITIVE LOGITS
    DITION
    0.08
    bett
    0.08
    fav
    0.08
     davon
    0.07
    umbo
    0.07
    MESS
    0.07
    _QUOTES
    0.07
    istrovstvÃŃ
    0.07
    GREE
    0.07
    ãİ
    0.07
    Activations Density 0.016%

    No Known Activations