© 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. 42147
    Prev
    Next
    INDEX
    Explanations

    calls to action related to reading or obtaining more information

    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
    hoff
    -0.07
    glich
    -0.07
    pone
    -0.07
    ephy
    -0.07
    uchs
    -0.07
    ledon
    -0.06
    ajes
    -0.06
    partment
    -0.06
    assen
    -0.06
    asa
    -0.06
    POSITIVE LOGITS
    ings
    0.11
    ily
    0.07
    ers
    0.07
    omb
    0.07
    unk
    0.07
    INGS
    0.07
    ra
    0.07
    aira
    0.06
    able
    0.06
    along
    0.06
    Activations Density 0.015%

    No Known Activations