© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124914
    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
     tá»Ń
    -0.07
    -&
    -0.06
    agh
    -0.06
    licht
    -0.06
    ãĥ¼ãĥģ
    -0.06
    yr
    -0.05
     wz
    -0.05
     &
    -0.05
    SCRIPTOR
    -0.05
    H
    -0.05
    POSITIVE LOGITS
    uct
    0.07
    eness
    0.07
    itarian
    0.07
     amac
    0.07
    SenderId
    0.07
    leness
    0.07
    å§ĵ
    0.07
     azal
    0.06
    _done
    0.06
    UTF
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.