© 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. 118877
    Prev
    Next
    INDEX
    Explanations

    important concepts related to achievement and success

    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
    addock
    -0.08
    éļ
    -0.07
    AGO
    -0.07
    upon
    -0.07
     Swinger
    -0.06
     techn
    -0.06
    ãİ
    -0.06
    _Find
    -0.06
    lém
    -0.06
    anders
    -0.06
    POSITIVE LOGITS
    verage
    0.07
    -Compatible
    0.07
    arel
    0.06
    amacare
    0.06
    çļĦå¿ĥ
    0.06
    pliers
    0.06
    logan
    0.06
    adir
    0.06
    aren
    0.06
    pollo
    0.06
    Activations Density 0.047%

    No Known Activations