© 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 EvalsExportsinterp-engineNEWAPI 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. 42165
    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
    enha
    -0.07
    endor
    -0.06
    amentals
    -0.06
    hawk
    -0.06
    jug
    -0.06
    949
    -0.06
    CompatActivity
    -0.06
    rts
    -0.06
     longitudinal
    -0.06
    ή
    -0.06
    POSITIVE LOGITS
     mattress
    0.08
     bed
    0.07
     SZ
    0.07
     Bed
    0.07
    latex
    0.06
     Cz
    0.06
    åºĬ
    0.06
     Matt
    0.06
    rz
    0.06
    _pg
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.