Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96247
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "dangerous" and related concepts

    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
    cken
    -0.08
    usk
    -0.08
    GenerationStrategy
    -0.07
    onas
    -0.07
    eday
    -0.07
    sey
    -0.07
    å±
    -0.07
    onica
    -0.07
    ambda
    -0.06
    onte
    -0.06
    POSITIVE LOGITS
    ness
    0.08
    -looking
    0.07
     enough
    0.07
    OperationException
    0.07
    -danger
    0.07
     Enough
    0.07
     dangerous
    0.07
    à¸ĵ
    0.07
    -grade
    0.07
     yere
    0.06
    Activations Density 0.009%

    No Known Activations