© 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. 16354
    Prev
    Next
    INDEX
    Explanations

    numerical values representing counts or identifiers

    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
     or
    -0.06
    -0.06
     for
    -0.06
     sne
    -0.06
     ,
    -0.05
     -
    -0.05
    boy
    -0.05
    ound
    -0.05
    one
    -0.05
     #
    -0.05
    POSITIVE LOGITS
    opa
    0.08
    querque
    0.07
    å¢
    0.07
    peri
    0.07
     yazılı
    0.07
    zte
    0.07
    _cg
    0.07
     åıĮ线
    0.07
     POLITICO
    0.07
    mî
    0.07
    Activations Density 0.001%

    No Known Activations