© 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. 17-LLAMASCOPE-RES-131K
    11. 77442
    Prev
    Next
    INDEX
    Explanations

    the presence of approval or endorsement for a product

    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
    pery
    -0.07
    alie
    -0.07
    inja
    -0.06
    gies
    -0.06
    tres
    -0.06
    atchet
    -0.06
    اÙĦت
    -0.06
    lobs
    -0.06
     predecess
    -0.06
    yon
    -0.06
    POSITIVE LOGITS
    pais
    0.07
    roid
    0.07
    ikk
    0.06
    etÃł
    0.06
     Branch
    0.06
    æĬ¥
    0.06
    olson
    0.06
    etak
    0.06
     Dort
    0.06
    .trailing
    0.06
    Activations Density 0.000%

    No Known Activations