© 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. 28218
    Prev
    Next
    INDEX
    Explanations

    significant phrases and elements that signify consequence or conditions

    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
    chw
    -0.08
    akis
    -0.07
    imizer
    -0.07
    ยà¸ģ
    -0.07
    IZER
    -0.07
     DISCLAIM
    -0.07
    ardon
    -0.06
    ÑĸлÑĮ
    -0.06
    izer
    -0.06
    .bumptech
    -0.06
    POSITIVE LOGITS
     police
    0.15
     crime
    0.13
     Police
    0.12
     security
    0.11
    Police
    0.11
     Crime
    0.10
    -security
    0.10
     Security
    0.09
     law
    0.09
     safety
    0.09
    Activations Density 0.010%

    No Known Activations