© 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. 3403
    Prev
    Next
    INDEX
    Explanations

    references to demons and related supernatural entities

    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
    weise
    -0.09
    urret
    -0.07
    -wise
    -0.06
    iffin
    -0.06
    zier
    -0.06
    еÑĢÑĪ
    -0.06
    alon
    -0.06
    åŃĿ
    -0.06
    uffers
    -0.06
    aurus
    -0.06
    POSITIVE LOGITS
    /dev
    0.09
    raz
    0.07
     possession
    0.07
    éİ®
    0.07
    ë
    0.07
    like
    0.06
    ög
    0.06
    buster
    0.06
    gram
    0.06
    uous
    0.06
    Activations Density 0.021%

    No Known Activations