© 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. 128831
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their credentials in the context of literature or academia

    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
    eder
    -0.07
     which
    -0.07
     var
    -0.06
    ober
    -0.06
    ees
    -0.06
    ----
    -0.06
    oi
    -0.06
    orris
    -0.06
    etc
    -0.06
    aim
    -0.06
    POSITIVE LOGITS
    URLException
    0.09
    ofday
    0.09
    $MESS
    0.08
    tdown
    0.07
     migrationBuilder
    0.07
     author
    0.07
    actionDate
    0.07
    /tos
    0.07
    milliseconds
    0.07
    @nate
    0.07
    Activations Density 0.002%

    No Known Activations