© 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. 27188
    Prev
    Next
    INDEX
    Explanations

    themes related to death and violence

    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
    790
    -0.07
    ann
    -0.06
     recovery
    -0.06
    843
    -0.06
    odes
    -0.06
    lac
    -0.06
     doby
    -0.06
    ouns
    -0.06
    quin
    -0.06
     Burl
    -0.06
    POSITIVE LOGITS
    addon
    0.07
    UpInside
    0.07
    .gdx
    0.07
     by
    0.07
     Fallon
    0.06
    olson
    0.06
     laut
    0.06
    Hung
    0.06
    kuk
    0.06
    chter
    0.06
    Activations Density 0.021%

    No Known Activations