© 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. 76591
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to performance or achievements

    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
    0
    -0.07
    2
    -0.06
    X
    -0.06
    _
    -0.06
    3
    -0.06
    ged
    -0.06
    onec
    -0.06
    708
    -0.06
    esh
    -0.06
     Limits
    -0.06
    POSITIVE LOGITS
    #ad
    0.10
    #ab
    0.09
    ãģıãģł
    0.09
    peria
    0.09
    .bunifuFlatButton
    0.08
    udu
    0.08
    ãģıãĤĵ
    0.08
    #af
    0.08
     ----------------------------------------------------------------------------↵
    0.08
    .Reporting
    0.08
    Activations Density 0.100%

    No Known Activations