© 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. 15-LLAMASCOPE-RES-131K
    11. 89919
    Prev
    Next
    INDEX
    Explanations

    items and topics related to art and food

    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
    maal
    -0.07
    utta
    -0.07
    skip
    -0.06
     SKIP
    -0.06
    ennent
    -0.06
    ward
    -0.06
     Chall
    -0.06
    lund
    -0.06
    éij
    -0.06
     occupied
    -0.06
    POSITIVE LOGITS
     Corn
    0.06
    úc
    0.06
    anela
    0.06
     Cornell
    0.06
    cratch
    0.06
     modern
    0.06
     Dirt
    0.06
     à¤ıà¤ľ
    0.06
    Äįer
    0.06
    aux
    0.06
    Activations Density 0.027%

    No Known Activations