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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29643
    Prev
    Next
    INDEX
    Explanations

    discussions about health, well-being, and personal improvement strategies

    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
    oq
    -0.07
    .AutoComplete
    -0.07
    aeper
    -0.07
    luet
    -0.06
    reeze
    -0.06
    rych
    -0.06
    illez
    -0.06
    mega
    -0.06
    anel
    -0.06
    {\"
    -0.06
    POSITIVE LOGITS
     otherwise
    0.06
    odÃŃ
    0.06
    rub
    0.06
    IRS
    0.06
    blas
    0.06
     fich
    0.06
     parch
    0.06
    BCM
    0.06
    sass
    0.06
    irsch
    0.06
    Activations Density 0.639%

    No Known Activations