© 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. 17-LLAMASCOPE-RES-131K
    11. 40578
    Prev
    Next
    INDEX
    Explanations

    references to police accountability and justice

    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
    liga
    -0.08
    ixer
    -0.08
     schö
    -0.07
    çı
    -0.07
    寧
    -0.06
     Fou
    -0.06
    herits
    -0.06
    ddit
    -0.06
    IVES
    -0.06
    olvers
    -0.06
    POSITIVE LOGITS
     ones
    0.06
    anna
    0.06
     oh
    0.06
    yro
    0.05
    engl
    0.05
    ziel
    0.05
    '
    0.05
    rej
    0.05
     yearly
    0.05
     apl
    0.05
    Activations Density 0.001%

    No Known Activations