© 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. 15-LLAMASCOPE-RES-131K
    11. 86325
    Prev
    Next
    INDEX
    Explanations

    links to Twitter resources

    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
    uron
    -0.07
    raud
    -0.07
    sad
    -0.06
    erde
    -0.06
    ead
    -0.06
    endar
    -0.06
    dead
    -0.06
    292
    -0.06
    sen
    -0.06
    ipt
    -0.06
    POSITIVE LOGITS
     é¢
    0.06
    anoia
    0.06
    TextEdit
    0.06
    izza
    0.06
    ÙĪارÙĩ
    0.06
    itelist
    0.06
    essler
    0.06
    _Pin
    0.06
    pyx
    0.06
    ä½µ
    0.06
    Activations Density 0.000%

    No Known Activations