© 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. 76655
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of searching or discovering information

    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
    ints
    -0.07
     hydr
    -0.07
    ette
    -0.06
    reak
    -0.06
    æĥ
    -0.06
    à¥įषण
    -0.06
    bye
    -0.06
    é²ľ
    -0.06
    akest
    -0.06
    insi
    -0.06
    POSITIVE LOGITS
    /Runtime
    0.07
    IData
    0.06
    DOMNode
    0.06
    áze
    0.06
    zee
    0.06
    'gc
    0.06
    rup
    0.06
    ÏĢον
    0.06
    ISR
    0.06
    ercise
    0.06
    Activations Density 0.006%

    No Known Activations