© 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. 107636
    Prev
    Next
    INDEX
    Explanations

    references to verification and investigation processes

    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
    ATAR
    -0.07
     practition
    -0.07
    toc
    -0.07
    plorer
    -0.07
    defs
    -0.07
    ALER
    -0.07
    quil
    -0.07
    è«
    -0.07
     Rosenstein
    -0.06
    ustos
    -0.06
    POSITIVE LOGITS
     checks
    0.12
     check
    0.12
     verification
    0.11
     checking
    0.11
     ver
    0.11
     verify
    0.10
     verifying
    0.10
     vér
    0.10
     Verify
    0.10
     verifica
    0.10
    Activations Density 0.032%

    No Known Activations