© 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. 4583
    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
    ÙĦاÙĦ
    -0.07
    474
    -0.07
     caf
    -0.06
    nze
    -0.06
    Äĥ
    -0.06
    AF
    -0.06
    ncia
    -0.06
     af
    -0.06
    _exempt
    -0.06
    å¼
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĤ°ãĥ«
    0.07
    há
    0.07
    uo
    0.06
    conto
    0.06
    ãĥ¼ãĥķ
    0.06
     Singap
    0.06
    gorm
    0.06
     McGu
    0.06
    á»ijn
    0.06
    atom
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.