© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125347
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" indicating purpose or direction

    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
    heimer
    -0.08
    sanitize
    -0.06
    ãģį
    -0.06
    ultiply
    -0.06
    erties
    -0.06
    isation
    -0.06
    sky
    -0.06
    wdx
    -0.06
    isions
    -0.06
    (IR
    -0.06
    POSITIVE LOGITS
    xic
    0.07
    oret
    0.07
    ÑĤÑİ
    0.07
    maal
    0.07
    kon
    0.07
    éĥ
    0.07
    ungle
    0.06
    AINS
    0.06
    cest
    0.06
    ARGE
    0.06
    Activations Density 0.018%

    No Known Activations