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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 812
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and courtroom context

    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
    ccione
    -0.09
    gression
    -0.07
     (č↵
    -0.06
    _PREVIEW
    -0.06
    agher
    -0.06
    ivor
    -0.06
    .cms
    -0.06
    /plain
    -0.06
    ché
    -0.06
    )((((
    -0.06
    POSITIVE LOGITS
    amd
    0.06
     Hancock
    0.06
     hearing
    0.06
     session
    0.06
     appearance
    0.06
    lamaz
    0.06
     Bam
    0.06
    ocene
    0.06
    /status
    0.06
    urope
    0.06
    Activations Density 0.009%

    No Known Activations