© 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. 70180
    Prev
    Next
    INDEX
    Explanations

    influential adjectives and descriptors preceding nouns

    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
    berger
    -0.07
     feat
    -0.06
    ama
    -0.06
    having
    -0.06
    ezi
    -0.06
    .ie
    -0.06
     zas
    -0.06
    istas
    -0.06
     having
    -0.06
    ibe
    -0.06
    POSITIVE LOGITS
     chance
    0.08
    Ú¯ÛĮرÛĮ
    0.08
    лан
    0.08
    eed
    0.08
     reason
    0.08
     danger
    0.07
    .truth
    0.07
    _codegen
    0.07
    bilt
    0.07
    uder
    0.07
    Activations Density 0.049%

    No Known Activations