Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76596
    Prev
    Next
    INDEX
    Explanations

    terms associated with biographies

    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
    éľ²
    -0.07
     NÄĽm
    -0.06
    гаÑĢ
    -0.06
    ãĥł
    -0.06
    hoe
    -0.06
     Clim
    -0.06
     åĥ
    -0.06
    &w
    -0.06
    sole
    -0.06
     Sist
    -0.06
    POSITIVE LOGITS
     background
    0.08
    Background
    0.07
     Background
    0.07
    alink
    0.07
    background
    0.06
     kariy
    0.06
    -background
    0.06
    reten
    0.06
    adb
    0.06
    KO
    0.06
    Activations Density 0.002%

    No Known Activations