© 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. 94786
    Prev
    Next
    INDEX
    Explanations

    classes related to visual elements or formatting

    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
    imi
    -0.07
    theless
    -0.07
    ber
    -0.07
    osi
    -0.07
    asty
    -0.07
    ooks
    -0.07
    chestra
    -0.07
     McCoy
    -0.07
    lop
    -0.07
    etheless
    -0.07
    POSITIVE LOGITS
     Garr
    0.10
    mates
    0.07
    ="
    0.07
    ollipop
    0.07
    (es
    0.07
    mate
    0.06
    qing
    0.06
    imli
    0.06
     "
    0.06
    ä¼¼
    0.06
    Activations Density 0.012%

    No Known Activations