© 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. 75556
    Prev
    Next
    INDEX
    Explanations

    references to multimedia transformation and related processes

    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
    ums
    -0.07
    _indexes
    -0.07
     Ras
    -0.06
    aval
    -0.06
    athy
    -0.06
    atham
    -0.06
     Duo
    -0.06
    702
    -0.06
    pl
    -0.06
    778
    -0.06
    POSITIVE LOGITS
    erken
    0.07
    kus
    0.07
    .ua
    0.07
    té
    0.07
    rupted
    0.07
    idon
    0.07
    gross
    0.06
    .timing
    0.06
    .radioButton
    0.06
    zek
    0.06
    Activations Density 0.000%

    No Known Activations