© 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. 72816
    Prev
    Next
    INDEX
    Explanations

    qualifiers and adverbs that modify the intensity or frequency of actions or descriptions

    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
    obb
    -0.07
    onas
    -0.07
    aug
    -0.06
    okit
    -0.06
     пÑĥ
    -0.06
    èĥ¡
    -0.06
     ActionTypes
    -0.06
     èĥ
    -0.06
    ories
    -0.06
    astr
    -0.06
    POSITIVE LOGITS
    illions
    0.08
    æľī人
    0.08
    obody
    0.07
     addCriterion
    0.07
    indic
    0.07
    avit
    0.07
     NavParams
    0.07
    everyone
    0.07
    ÙıÙĪÙĨ
    0.06
     everyone
    0.06
    Activations Density 0.052%

    No Known Activations