© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128680
    Prev
    Next
    INDEX
    Explanations

    information related to episode counts and seasons in a television series

    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
    velt
    -0.07
    aits
    -0.07
    imb
    -0.07
    .priv
    -0.07
    fé
    -0.07
    彦
    -0.07
    èm
    -0.07
    anguard
    -0.06
    stp
    -0.06
    OrCreate
    -0.06
    POSITIVE LOGITS
     throughout
    0.07
     Wish
    0.07
     only
    0.06
     Throughout
    0.06
    è
    0.06
     seasons
    0.06
     recon
    0.06
    -feature
    0.06
    redient
    0.06
    AYS
    0.06
    Activations Density 0.002%

    No Known Activations