© 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. 70301
    Prev
    Next
    INDEX
    Explanations

    statements or declarations of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    -E
    -0.06
     Ham
    -0.06
    ãĥĿãĤ¤ãĥ³ãĥĪ
    -0.05
    XP
    -0.05
     Emerson
    -0.05
     Wilkinson
    -0.05
     C
    -0.05
    cha
    -0.05
    ;element
    -0.05
     ve
    -0.05
    POSITIVE LOGITS
     Ramsey
    0.07
    Æ°u
    0.07
    ignon
    0.06
    .cycle
    0.06
    htub
    0.06
    .habbo
    0.06
    nore
    0.06
    ERRU
    0.06
    afia
    0.06
    ushman
    0.06
    Activations Density 0.000%

    No Known Activations