© 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. 69534
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Erin."

    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
    asca
    -0.08
    жд
    -0.07
    richt
    -0.07
    tk
    -0.07
     addCriterion
    -0.06
    iterr
    -0.06
    adge
    -0.06
    Parms
    -0.06
    Ñīи
    -0.06
    gp
    -0.06
    POSITIVE LOGITS
    sey
    0.08
    atan
    0.07
    athers
    0.07
    .BorderSize
    0.07
    odal
    0.06
    æ´ŀ
    0.06
    field
    0.06
    नल
    0.06
    çon
    0.06
    bellion
    0.06
    Activations Density 0.002%

    No Known Activations