© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126052
    Prev
    Next
    INDEX
    Explanations

    references to clichés in various contexts

    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
    lier
    -0.07
    aq
    -0.06
    aris
    -0.06
    ré
    -0.06
     Kern
    -0.06
    lines
    -0.06
    еÑĨ
    -0.06
    /REC
    -0.06
    acific
    -0.06
    ayload
    -0.06
    POSITIVE LOGITS
    á»ĵng
    0.11
    ical
    0.08
    ippi
    0.08
    еви
    0.07
    ä¼¼
    0.07
    à¥įà¤ļ
    0.07
    ewise
    0.07
    hammer
    0.07
    PPER
    0.07
    .heroku
    0.07
    Activations Density 0.002%

    No Known Activations