© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56937
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to movement and action

    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
    ÐIJÑĢÑħÑĸв
    -0.07
    orb
    -0.07
     competition
    -0.06
    ç«ŀ
    -0.06
     Competition
    -0.06
    ارج
    -0.06
    azio
    -0.06
    .trim
    -0.06
    .BorderFactory
    -0.06
    zza
    -0.06
    POSITIVE LOGITS
     Imm
    0.08
    ocha
    0.07
    ahlen
    0.07
    ải
    0.07
    fel
    0.07
    èĮĤ
    0.07
     Gamer
    0.06
    indr
    0.06
     adv
    0.06
    323
    0.06
    Activations Density 0.001%

    No Known Activations