© 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. 9-LLAMASCOPE-RES-131K
    11. 96892
    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
    enger
    -0.07
    416
    -0.06
    奴
    -0.06
    à¸ī
    -0.06
    vido
    -0.06
    415
    -0.05
     Nail
    -0.05
    è¿«
    -0.05
    NER
    -0.05
    akk
    -0.05
    POSITIVE LOGITS
    ernel
    0.08
    Spoiler
    0.07
     gif
    0.07
    coma
    0.07
    å°
    0.07
    ILLISECONDS
    0.07
    Ĥ
    0.07
    ãĥĭãĤ¢
    0.07
    osoph
    0.07
    oriously
    0.07
    Activations Density 0.000%

    No Known Activations