© 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. 58883
    Prev
    Next
    INDEX
    Explanations

    expressions of disappointment or regret

    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
     type
    -0.06
    bes
    -0.06
    ved
    -0.06
    izzare
    -0.05
     Basic
    -0.05
    pts
    -0.05
    OPS
    -0.05
    GS
    -0.05
    /J
    -0.05
    utin
    -0.05
    POSITIVE LOGITS
    theValue
    0.07
     anale
    0.07
    áce
    0.07
    elow
    0.07
    ISIBLE
    0.07
    ÙĦÙĬÙħ
    0.07
     rằng
    0.07
    誤
    0.07
    ewe
    0.07
    ÑĤаÑĢ
    0.07
    Activations Density 0.004%

    No Known Activations