© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2843
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    OUCH
    -0.06
    onic
    -0.06
    ots
    -0.06
    é¡ĺãģĦ
    -0.06
    rio
    -0.06
     clue
    -0.06
     prior
    -0.06
     others
    -0.06
     typical
    -0.06
    (Gravity
    -0.06
    POSITIVE LOGITS
    GBK
    0.07
    èŃ
    0.07
    über
    0.07
    odule
    0.06
    éĬ·
    0.06
    itm
    0.06
     handjob
    0.06
    pars
    0.06
    gor
    0.06
     misunder
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.