© 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. 15-LLAMASCOPE-RES-131K
    11. 659
    Prev
    Next
    INDEX
    Explanations

    actions related to standing or physical positioning

    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
    bout
    -0.08
    ernel
    -0.08
    fty
    -0.08
    ispens
    -0.08
    ICLE
    -0.07
    pekt
    -0.07
    ambre
    -0.07
     ÑģоÑĢ
    -0.07
    aina
    -0.07
    dda
    -0.07
    POSITIVE LOGITS
     Pier
    0.07
     Tent
    0.07
    iger
    0.06
     Berger
    0.06
     Fu
    0.06
     hor
    0.06
    285
    0.05
     pi
    0.05
     tent
    0.05
     PI
    0.05
    Activations Density 0.000%

    No Known Activations