© 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. 106874
    Prev
    Next
    INDEX
    Explanations

    occurrences of denial or negation

    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
    orem
    -0.07
     Ja
    -0.07
    .Magenta
    -0.06
    ETY
    -0.06
    Ja
    -0.06
    egg
    -0.06
     McCl
    -0.06
    oe
    -0.06
    anca
    -0.06
    è¼
    -0.06
    POSITIVE LOGITS
    ombo
    0.07
    amarin
    0.06
    -License
    0.06
    aturing
    0.06
    alion
    0.06
    warnings
    0.06
    ivalence
    0.06
    achable
    0.06
     Drugs
    0.06
     EZ
    0.06
    Activations Density 0.011%

    No Known Activations