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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 107899
    Prev
    Next
    INDEX
    Explanations

    technical identifiers or components related to code and data structures

    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
    juan
    -0.08
    368
    -0.06
    416
    -0.06
    horn
    -0.06
    hint
    -0.06
    wich
    -0.06
    gren
    -0.06
     Patterns
    -0.05
    478
    -0.05
     divid
    -0.05
    POSITIVE LOGITS
    @qq
    0.10
    serter
    0.08
    ross
    0.07
    oint
    0.07
    ROSS
    0.07
    ubble
    0.07
    WEBPACK
    0.06
     ?>"/>↵
    0.06
    fts
    0.06
    _COMM
    0.06
    Activations Density 0.014%

    No Known Activations