© 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. 89068
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    upper
    -0.07
    ots
    -0.06
    artner
    -0.06
     minHeight
    -0.06
    },'
    -0.06
     easing
    -0.06
    Longrightarrow
    -0.06
    andle
    -0.05
    ackets
    -0.05
    425
    -0.05
    POSITIVE LOGITS
    ystack
    0.07
    getc
    0.07
    ichen
    0.07
    ingo
    0.07
    _COMPILE
    0.07
    _Email
    0.07
    ë²Ī
    0.07
    efon
    0.07
    å±
    0.06
    madan
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.