© 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. 76167
    Prev
    Next
    INDEX
    Explanations

    references to family-related terms

    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
    åħį
    -0.08
    eden
    -0.07
    peria
    -0.07
    anut
    -0.07
    issor
    -0.07
    omers
    -0.07
    edic
    -0.06
    ilm
    -0.06
    elia
    -0.06
     åħį
    -0.06
    POSITIVE LOGITS
    ship
    0.07
    adero
    0.06
    aps
    0.06
    ceipt
    0.06
    essaging
    0.06
     Animalia
    0.06
    lement
    0.06
     extended
    0.06
    647
    0.06
    acements
    0.06
    Activations Density 0.001%

    No Known Activations