© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42470
    Prev
    Next
    INDEX
    Explanations

    words expressing excitement, energy, or chaotic events

    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
    .pretty
    -0.07
    emade
    -0.07
    vanced
    -0.07
    _USED
    -0.07
    æľĭ
    -0.07
    contres
    -0.06
    askell
    -0.06
    /Branch
    -0.06
     Miner
    -0.06
    zilla
    -0.06
    POSITIVE LOGITS
     Scre
    0.07
     happening
    0.07
     Happ
    0.06
    /errors
    0.06
     Recomm
    0.06
     ocur
    0.06
     happen
    0.06
    åįĵ
    0.06
    ous
    0.06
    averse
    0.06
    Activations Density 0.032%

    No Known Activations