© 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. 9-LLAMASCOPE-RES-131K
    11. 95371
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting elements typical in technical or programming contexts

    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
    CPP
    -0.08
    ruby
    -0.07
    _cg
    -0.07
    plib
    -0.07
    ufe
    -0.07
    exus
    -0.06
    ruž
    -0.06
    esini
    -0.06
    GetProperty
    -0.06
    elsing
    -0.06
    POSITIVE LOGITS
    Æ¡
    0.06
    rio
    0.06
    angan
    0.06
    scape
    0.06
    ace
    0.06
     -------------------------------------------------------------------------
    0.06
    cheid
    0.06
    LastError
    0.06
     Dial
    0.05
    rip
    0.05
    Activations Density 0.010%

    No Known Activations