© 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. 118920
    Prev
    Next
    INDEX
    Explanations

    identifiers and tags related to Google Analytics tracking

    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
    ippi
    -0.08
    lien
    -0.07
    MethodImpl
    -0.07
    jian
    -0.07
    ollider
    -0.07
    wares
    -0.07
    ijken
    -0.06
    onden
    -0.06
     kvin
    -0.06
    hani
    -0.06
    POSITIVE LOGITS
     Deck
    0.06
    pector
    0.06
    anning
    0.06
    GLOSS
    0.06
    Deck
    0.06
    ÑĢива
    0.06
     dawn
    0.06
     Jog
    0.06
     Gut
    0.06
    257
    0.06
    Activations Density 0.006%

    No Known Activations