© 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. 16295
    Prev
    Next
    INDEX
    Explanations

    relationships within family histories

    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
    ayer
    -0.07
    ñana
    -0.06
    esses
    -0.06
    ,arg
    -0.06
     åĬ
    -0.05
    ampp
    -0.05
     recharge
    -0.05
     Noon
    -0.05
    ekl
    -0.05
     çĬ
    -0.05
    POSITIVE LOGITS
     gene
    0.07
    ï¼ĪæĺŃåĴĮ
    0.07
    iline
    0.07
    orsk
    0.07
    npj
    0.07
    memory
    0.07
     trÃŃ
    0.07
     entrev
    0.07
     interviewed
    0.07
    itone
    0.07
    Activations Density 0.019%

    No Known Activations