© 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. 55810
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or actions

    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
    ataka
    -0.08
    ho
    -0.07
    ryn
    -0.07
    lah
    -0.06
     Parallel
    -0.06
    hol
    -0.06
    iston
    -0.06
    aná
    -0.06
    ÙĥÙĦ
    -0.06
    UNT
    -0.06
    POSITIVE LOGITS
    walk
    0.08
     walk
    0.07
     walked
    0.07
    Walk
    0.07
     motion
    0.07
    .motion
    0.07
    æ´»
    0.06
    walking
    0.06
     walks
    0.06
    walker
    0.06
    Activations Density 0.017%

    No Known Activations