© 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. 17-LLAMASCOPE-RES-131K
    11. 77577
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    :params
    -0.07
    ijd
    -0.06
    otch
    -0.06
    )prepare
    -0.06
    ãĤĪãģŃ
    -0.06
     parms
    -0.06
    LOBAL
    -0.06
    ака
    -0.05
    inia
    -0.05
    ')."
    -0.05
    POSITIVE LOGITS
    velt
    0.07
    ettel
    0.07
     ourselves
    0.07
     Citizen
    0.06
    bern
    0.06
    icken
    0.06
    ivil
    0.06
    itizen
    0.06
     citizen
    0.06
    ¥¿
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.