© 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. 17-LLAMASCOPE-RES-131K
    11. 89153
    Prev
    Next
    INDEX
    Explanations

    complaints and criticisms about experiences or products

    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
    ascar
    -0.06
     Reject
    -0.06
    ĤŃ
    -0.06
    RB
    -0.06
    IMATE
    -0.06
    IfNeeded
    -0.06
    efa
    -0.06
    öt
    -0.06
     interesting
    -0.06
    åŀ
    -0.06
    POSITIVE LOGITS
     minor
    0.09
    minor
    0.08
     nit
    0.08
    Minor
    0.07
     Nit
    0.07
     Complaint
    0.07
    Nit
    0.06
     Minor
    0.06
    nit
    0.06
     ncols
    0.06
    Activations Density 0.014%

    No Known Activations