© 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. 95504
    Prev
    Next
    INDEX
    Explanations

    references to collars and collateral damage 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
    ening
    -0.09
    gie
    -0.09
    y
    -0.09
    eck
    -0.08
    dde
    -0.08
    ema
    -0.08
    vvm
    -0.08
    anning
    -0.08
    else
    -0.08
    eler
    -0.08
    POSITIVE LOGITS
    ory
    0.07
    avec
    0.07
    idge
    0.07
    bone
    0.06
    l
    0.06
    one
    0.06
    ORY
    0.06
    /el
    0.06
    ution
    0.06
    oll
    0.06
    Activations Density 0.002%

    No Known Activations