© 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. 87580
    Prev
    Next
    INDEX
    Explanations

    the name "Mitchell" and its variations

    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
    nit
    -0.08
     Äijiá»ĥn
    -0.08
    irket
    -0.08
    yms
    -0.07
    ein
    -0.07
    iring
    -0.07
    viz
    -0.07
    zioni
    -0.06
    obox
    -0.06
    eden
    -0.06
    POSITIVE LOGITS
     latter
    0.08
    sonian
    0.08
    iana
    0.08
    urst
    0.07
    bilt
    0.07
    burg
    0.06
    woord
    0.06
    iner
    0.06
    lah
    0.06
    fork
    0.06
    Activations Density 0.007%

    No Known Activations