© 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. 57155
    Prev
    Next
    INDEX
    Explanations

    the presence of script elements 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
    otos
    -0.06
    api
    -0.06
    ÑĥлÑİ
    -0.06
     UIG
    -0.06
    load
    -0.06
    emer
    -0.06
    assed
    -0.06
     Keys
    -0.06
     Mist
    -0.06
    apl
    -0.06
    POSITIVE LOGITS
    _preference
    0.06
    uelles
    0.06
     offending
    0.06
    .Experimental
    0.06
    Commerce
    0.06
    ç¿°
    0.06
    AnimationFrame
    0.06
    ty
    0.06
    mpr
    0.06
    cps
    0.06
    Activations Density 0.000%

    No Known Activations