© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129755
    Prev
    Next
    INDEX
    Explanations

    references to imprisonment and legal proceedings

    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
    ija
    -0.07
    etic
    -0.06
     prosecutions
    -0.06
     Jah
    -0.06
    ette
    -0.06
    stdin
    -0.06
    )(((
    -0.06
    ADIUS
    -0.06
     conscience
    -0.06
    Äĥr
    -0.06
    POSITIVE LOGITS
     release
    0.10
    .release
    0.09
     Release
    0.09
    release
    0.09
    Release
    0.08
    .Release
    0.08
     charges
    0.08
    Released
    0.08
     RELEASE
    0.08
     releasing
    0.08
    Activations Density 0.026%

    No Known Activations