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. 119298
    Prev
    Next
    INDEX
    Explanations

    references to alliances and partnerships

    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
    clamp
    -0.08
    иÑĤÑĭ
    -0.08
    ازÙĦ
    -0.07
    PELL
    -0.07
    ức
    -0.07
    istas
    -0.07
    melon
    -0.07
    jang
    -0.07
    ista
    -0.07
    fila
    -0.07
    POSITIVE LOGITS
    ship
    0.10
    ships
    0.10
    /helper
    0.09
    hood
    0.08
    liness
    0.07
    ssa
    0.07
    dom
    0.07
    ington
    0.07
    /support
    0.06
    SHIP
    0.06
    Activations Density 0.007%

    No Known Activations