© 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. 70321
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of "Shepherd."

    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
    t
    -0.09
    e
    -0.09
    eos
    -0.07
    gger
    -0.07
    eration
    -0.06
    eon
    -0.06
    ouz
    -0.06
    AYER
    -0.06
    yu
    -0.06
    eus
    -0.06
    POSITIVE LOGITS
    rones
    0.08
    ìĦľëĬĶ
    0.07
    ries
    0.07
    erv
    0.07
    stown
    0.07
    ewe
    0.07
    ess
    0.07
     Ron
    0.07
    aight
    0.07
    skin
    0.07
    Activations Density 0.004%

    No Known Activations