© 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 EvalsExportsinterp-engineNEWAPI 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. 69639
    Prev
    Next
    INDEX
    Explanations

    references to 'arm' or 'arms' in various contexts

    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
    apur
    -0.08
    /problem
    -0.08
    볨
    -0.08
    ISM
    -0.08
    izer
    -0.07
    кап
    -0.07
    anism
    -0.07
    CTS
    -0.07
    Äįe
    -0.07
    ê¸ī
    -0.07
    POSITIVE LOGITS
    oured
    0.10
    chair
    0.09
    ament
    0.08
    strong
    0.08
    rest
    0.08
    /arm
    0.07
    illary
    0.07
    aged
    0.07
    ature
    0.07
    arm
    0.07
    Activations Density 0.019%

    No Known Activations