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

    Neuronpedia

    Jacobian LensNEW
    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. 119257
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of inability

    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
    å¢ĥ
    -0.08
    rex
    -0.08
    _FP
    -0.08
    à¥ģह
    -0.07
     '';č↵
    -0.07
    (Py
    -0.06
    AdapterFactory
    -0.06
    ccione
    -0.06
    ç¼
    -0.06
    енд
    -0.06
    POSITIVE LOGITS
    axe
    0.07
    verse
    0.06
     computer
    0.06
    munition
    0.06
    ervers
    0.06
    olle
    0.06
    innie
    0.06
    feld
    0.06
    ails
    0.06
     Malone
    0.06
    Activations Density 0.000%

    No Known Activations