© 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. 16617
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal recognition or judgment

    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
    onth
    -0.07
     Ãĸn
    -0.07
    rada
    -0.07
    nun
    -0.07
    ảy
    -0.07
    afx
    -0.07
    нок
    -0.07
    inx
    -0.06
    tero
    -0.06
    iken
    -0.06
    POSITIVE LOGITS
     having
    0.09
     being
    0.08
     what
    0.07
    thouse
    0.07
    having
    0.06
    ableObject
    0.06
    @mail
    0.06
     their
    0.06
     doing
    0.06
     id
    0.06
    Activations Density 0.017%

    No Known Activations