© 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. 9-LLAMASCOPE-RES-131K
    11. 95658
    Prev
    Next
    INDEX
    Explanations

    elements related to play and interactive activities for children

    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
    caret
    -0.07
    kip
    -0.06
    Ìģ
    -0.06
    anza
    -0.06
    master
    -0.06
    metric
    -0.06
    nic
    -0.06
     omn
    -0.06
    wij
    -0.06
    umba
    -0.06
    POSITIVE LOGITS
    isas
    0.08
    ulos
    0.07
    mand
    0.07
     Mand
    0.07
    acon
    0.06
    .cloudflare
    0.06
    .sax
    0.06
    Ĵ
    0.06
    ayla
    0.06
    ENSION
    0.06
    Activations Density 0.004%

    No Known Activations