© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61412
    Prev
    Next
    INDEX
    Explanations

    the term associated with mischief or wrongful behavior

    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
    Began
    -0.07
    اÙĨÙĪ
    -0.07
    libft
    -0.07
    ombo
    -0.07
    lobs
    -0.07
    prung
    -0.06
    atcher
    -0.06
    ÙĪغ
    -0.06
    иÑģк
    -0.06
    AttribPointer
    -0.06
    POSITIVE LOGITS
    innen
    0.07
    orne
    0.06
    if
    0.06
    kke
    0.06
     ones
    0.06
    odore
    0.06
    plan
    0.06
    ;s
    0.06
     rather
    0.06
     Blonde
    0.06
    Activations Density 0.000%

    No Known Activations