© 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. 27856
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions related to participation or interaction with content

    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
    ober
    -0.08
    isodes
    -0.08
    lom
    -0.07
    ape
    -0.07
    lemen
    -0.07
    -urlencoded
    -0.07
    amat
    -0.07
    ủ
    -0.07
    annon
    -0.07
     Morrow
    -0.07
    POSITIVE LOGITS
    461
    0.06
    UV
    0.06
     viewing
    0.05
     inland
    0.05
    uto
    0.05
     unt
    0.05
     dangerously
    0.05
     Dok
    0.05
    458
    0.05
    clamp
    0.05
    Activations Density 0.001%

    No Known Activations