© 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. 9-LLAMASCOPE-RES-131K
    11. 98980
    Prev
    Next
    INDEX
    Explanations

    prominent nouns and key terms in a technical context

    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
    gram
    -0.06
    ightly
    -0.06
    omething
    -0.06
    dep
    -0.06
    ses
    -0.06
    .refs
    -0.06
    ser
    -0.05
    кÑĥÑĢ
    -0.05
    der
    -0.05
    grams
    -0.05
    POSITIVE LOGITS
    oretical
    0.12
    atre
    0.10
    semble
    0.09
    oret
    0.08
    Sharper
    0.08
    pom
    0.07
    Æ¡i
    0.07
    ãĥ¼ãĥĦ
    0.07
    atten
    0.07
    CONF
    0.07
    Activations Density 0.020%

    No Known Activations