© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123527
    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
    Ú©ÛĮÙĦ
    -0.07
    IGIN
    -0.07
    elman
    -0.07
    ãĤ·ãĥ§ãĥ³
    -0.07
    TypeInfo
    -0.07
    εÏī
    -0.06
     NÄĽm
    -0.06
    ipt
    -0.06
    ahi
    -0.06
    ysz
    -0.06
    POSITIVE LOGITS
     Dunn
    0.07
    asive
    0.06
    ãģĿ
    0.06
    asha
    0.06
     Stan
    0.06
     ben
    0.06
     elim
    0.05
    orse
    0.05
    nesia
    0.05
     carg
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.