© 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. 124139
    Prev
    Next
    INDEX
    Explanations

    references to high achievements or records in career statistics

    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
    mess
    -0.07
    arcy
    -0.06
    ulus
    -0.06
    strand
    -0.06
    _MB
    -0.06
    noinspection
    -0.06
    eco
    -0.06
    neau
    -0.06
    ame
    -0.06
    igh
    -0.06
    POSITIVE LOGITS
    edly
    0.07
    SetBranch
    0.07
    ety
    0.07
    ingly
    0.07
    _simps
    0.07
    人çī©
    0.07
    /std
    0.07
    ensively
    0.07
    lan
    0.07
    egree
    0.07
    Activations Density 0.005%

    No Known Activations