© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117234
    Prev
    Next
    INDEX
    Explanations

    expressions of self-identity and personal reflection

    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
    ÑĦи
    -0.07
    (equalTo
    -0.07
    ÑĦÑĸ
    -0.07
    uko
    -0.06
    .TabIndex
    -0.06
     mass
    -0.06
    uki
    -0.06
    bolt
    -0.06
     norge
    -0.06
    Already
    -0.06
    POSITIVE LOGITS
     vain
    0.07
    YRO
    0.06
     partial
    0.06
     fond
    0.06
     active
    0.06
    able
    0.06
    ocking
    0.06
    ude
    0.06
     currently
    0.06
    _https
    0.06
    Activations Density 0.055%

    No Known Activations