Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 29470
    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
     deeply
    -0.06
     ÙĤÙĩر
    -0.06
    -back
    -0.05
     punch
    -0.05
    ius
    -0.05
    anc
    -0.05
     pro
    -0.05
    .Contracts
    -0.05
     corners
    -0.05
     compelling
    -0.05
    POSITIVE LOGITS
    imore
    0.07
     hen
    0.07
    ivery
    0.07
    unifu
    0.07
    asz
    0.07
    ziel
    0.07
    esiz
    0.07
    LEGRO
    0.07
    imary
    0.07
    riot
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.