© 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. 5104
    Prev
    Next
    INDEX
    Explanations

    elements related to themes of social representation and agency

    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
    phabet
    -0.06
    ruits
    -0.06
     recent
    -0.06
     currently
    -0.06
    esion
    -0.06
    ġ
    -0.06
    abbr
    -0.06
     local
    -0.06
     travers
    -0.06
    udder
    -0.06
    POSITIVE LOGITS
    Throughout
    0.07
    .jquery
    0.07
     Throughout
    0.07
     IMPLIED
    0.07
    sthrough
    0.07
     throughout
    0.07
     Pg
    0.07
    VL
    0.06
    omorphic
    0.06
    acus
    0.06
    Activations Density 0.004%

    No Known Activations