© 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. 105447
    Prev
    Next
    INDEX
    Explanations

    phrases and details related to firearms and their specifications

    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
    ubo
    -0.05
    isch
    -0.05
    437
    -0.05
    ajas
    -0.05
    ↵
    -0.05
    iams
    -0.05
    964
    -0.05
    YY
    -0.05
    ung
    -0.05
    438
    -0.05
    POSITIVE LOGITS
     anything
    0.22
     Anything
    0.21
    anything
    0.20
    Anything
    0.20
     any
    0.19
    ä»»ä½ķ
    0.17
    Any
    0.17
     Any
    0.17
     ANY
    0.17
    -any
    0.15
    Activations Density 0.091%

    No Known Activations