© 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. 9-LLAMASCOPE-RES-131K
    6. 95523
    Prev
    Next
    INDEX
    Explanations

    instances of attributed speech or statements made by individuals

    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
    .tap
    -0.07
    aland
    -0.07
     oslo
    -0.07
    ButtonModule
    -0.07
    ÃĸL
    -0.06
    bett
    -0.06
    kok
    -0.06
    gov
    -0.06
    OfFile
    -0.06
    rado
    -0.06
    POSITIVE LOGITS
    ishes
    0.06
    losed
    0.06
    reopen
    0.06
    pty
    0.06
    é¸
    0.06
     ê³łëł¤
    0.05
    .Border
    0.05
    aines
    0.05
    ango
    0.05
    etsy
    0.05
    Activations Density 0.009%

    No Known Activations