© 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. 15-LLAMASCOPE-RES-131K
    11. 62121
    Prev
    Next
    INDEX
    Explanations

    statements and contexts related to denial

    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
    anova
    -0.08
    leh
    -0.08
     jadx
    -0.07
    apis
    -0.07
    ettle
    -0.07
    _DOM
    -0.07
    ancellable
    -0.07
     üzerindeki
    -0.07
    @nate
    -0.07
    zan
    -0.07
    POSITIVE LOGITS
     access
    0.08
     existence
    0.07
     exist
    0.07
     exists
    0.07
    0.07
    asti
    0.06
    thumbs
    0.06
     us
    0.06
    077
    0.06
    orst
    0.06
    Activations Density 0.012%

    No Known Activations