© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26884
    Prev
    Next
    INDEX
    Explanations

    requests for donations or support

    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
    avez
    -0.06
    120
    -0.06
     bare
    -0.06
    yas
    -0.05
     unpaid
    -0.05
    u
    -0.05
    oid
    -0.05
     overall
    -0.05
    ByKey
    -0.05
    ist
    -0.05
    POSITIVE LOGITS
    lags
    0.09
    éĿ©
    0.08
    ICA
    0.07
    лаг
    0.07
    roje
    0.07
    ÅĻet
    0.07
    STALL
    0.07
    zier
    0.07
    .clf
    0.07
     ï¼ľ
    0.07
    Activations Density 0.017%

    No Known Activations