© 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. 41644
    Prev
    Next
    INDEX
    Explanations

    reflections on improvement and personal growth within 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
    ednou
    -0.07
    zman
    -0.06
    __',
    -0.06
    ìĿ´ìĬ¤
    -0.06
    ipes
    -0.06
    Freedom
    -0.06
    QualifiedName
    -0.06
    {{{
    -0.06
     pam
    -0.06
     cue
    -0.06
    POSITIVE LOGITS
     happen
    0.08
    icorn
    0.07
    ici
    0.07
    alink
    0.07
    icers
    0.06
    áf
    0.06
     supreme
    0.06
     Claw
    0.06
     Geh
    0.06
     happened
    0.06
    Activations Density 0.026%

    No Known Activations