© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87788
    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
    asco
    -0.08
    lut
    -0.07
    ýt
    -0.07
    ooled
    -0.07
    deme
    -0.06
    villa
    -0.06
    ácil
    -0.06
    ÙĬÙĨØ©
    -0.06
    åĪĬ
    -0.06
    ARIO
    -0.06
    POSITIVE LOGITS
     Bunlar
    0.07
    ModelProperty
    0.06
    otas
    0.06
     Rit
    0.06
    WSC
    0.06
     UsersController
    0.06
    cpy
    0.06
    jen
    0.06
    ÏĥÏĦά
    0.06
     Fou
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.