© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86248
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal or regulatory consequences

    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
    ázd
    -0.08
    udget
    -0.08
     migrationBuilder
    -0.08
    KHTML
    -0.08
    JNI
    -0.07
    ruba
    -0.07
    óst
    -0.07
    PostBack
    -0.07
    óż
    -0.07
    builtin
    -0.07
    POSITIVE LOGITS
     automatically
    0.08
     may
    0.06
     until
    0.06
     next
    0.06
     immediately
    0.06
    lok
    0.06
    onet
    0.06
     unless
    0.06
    ;
    0.06
     in
    0.06
    Activations Density 0.014%

    No Known Activations