© 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. 61887
    Prev
    Next
    INDEX
    Explanations

    phrases indicating regulatory or legal oversight

    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
    stoff
    -0.06
    itou
    -0.06
    ect
    -0.06
    unter
    -0.06
    ror
    -0.06
    ective
    -0.06
     Ùħرکز
    -0.05
    ìĤ¬ë¬´
    -0.05
     crossword
    -0.05
    دار
    -0.05
    POSITIVE LOGITS
     note
    0.09
    avian
    0.07
     Leaf
    0.07
    ahlen
    0.07
    oggle
    0.07
    appable
    0.06
    teness
    0.06
     Note
    0.06
    emean
    0.06
     bloom
    0.06
    Activations Density 0.022%

    No Known Activations