© 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. 74923
    Prev
    Next
    INDEX
    Explanations

    words related to people in transit or movement

    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
    avin
    -0.06
    ChangedEventArgs
    -0.06
    oui
    -0.06
    sher
    -0.06
    nova
    -0.06
    ingu
    -0.06
    VILLE
    -0.06
    orado
    -0.06
    timeofday
    -0.06
    chet
    -0.06
    POSITIVE LOGITS
     passing
    0.09
    аÑĩ
    0.08
     Passing
    0.07
    neath
    0.07
    pass
    0.06
    /post
    0.06
    over
    0.06
    occ
    0.06
     Jacobs
    0.06
    wa
    0.06
    Activations Density 0.002%

    No Known Activations