© 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 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. 16356
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the categorization or filing of content

    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
     Manus
    -0.06
    kv
    -0.06
    stem
    -0.06
    beth
    -0.06
    ance
    -0.06
    itori
    -0.06
    wyn
    -0.06
    mons
    -0.06
    apt
    -0.06
    vious
    -0.05
    POSITIVE LOGITS
    ÑĢаÐ
    0.07
     Rubin
    0.07
    .sax
    0.07
    баÑģ
    0.07
    Äįást
    0.07
    eah
    0.07
    fono
    0.07
    ReuseIdentifier
    0.06
     porr
    0.06
    rvine
    0.06
    Activations Density 0.000%

    No Known Activations