© 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. 62979
    Prev
    Next
    INDEX
    Explanations

    CSS media query rules related to screen sizes

    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
    oner
    -0.09
    mite
    -0.07
    esModule
    -0.07
    alin
    -0.07
    :\/\/
    -0.07
    .FC
    -0.07
    arpa
    -0.06
    enga
    -0.06
    lod
    -0.06
    å°½
    -0.06
    POSITIVE LOGITS
    اÙĨس
    0.07
    ãĥ©ãĥ³ãĥī
    0.07
     conditions
    0.06
    ContentSize
    0.06
     Pied
    0.06
    룴
    0.06
    ëįķ
    0.06
    ChangedEventArgs
    0.06
     Mega
    0.06
    deg
    0.06
    Activations Density 0.003%

    No Known Activations