© 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. 3501
    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
     &
    -0.06
     emanc
    -0.05
     Claw
    -0.05
    kus
    -0.05
    implify
    -0.05
    787
    -0.05
    775
    -0.05
     Copper
    -0.05
     '&
    -0.05
    },"
    -0.05
    POSITIVE LOGITS
    Äįel
    0.10
    ostel
    0.08
    oins
    0.08
    raÄį
    0.08
    Äįem
    0.08
    smarty
    0.08
    sheets
    0.07
    adal
    0.07
    orado
    0.07
    obia
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.