© 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. 128687
    Prev
    Next
    INDEX
    Explanations

    actions related to viewing or interacting with media

    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
     componentDid
    -0.07
     ÑģобоÑİ
    -0.07
    quo
    -0.07
     Ñģобой
    -0.07
    OwnProperty
    -0.07
    gain
    -0.06
    ermo
    -0.06
     actionTypes
    -0.06
     Rein
    -0.06
    ullen
    -0.06
    POSITIVE LOGITS
    æĽ´å¤ļ
    0.11
     enough
    0.10
     some
    0.10
     dozens
    0.09
     fewer
    0.09
     more
    0.09
     lots
    0.09
     numerous
    0.09
     many
    0.08
     several
    0.08
    Activations Density 0.039%

    No Known Activations