© 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. 17714
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly those related to significant figures or entities

    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
    nya
    -0.09
    ris
    -0.09
    z
    -0.09
    ri
    -0.09
    b
    -0.08
    pa
    -0.08
    pu
    -0.08
    ech
    -0.08
    ness
    -0.08
    tan
    -0.08
    POSITIVE LOGITS
    'nun
    0.10
    ’nun
    0.08
    ptions
    0.08
     vá»±c
    0.07
    wig
    0.07
    ipment
    0.07
    querque
    0.07
    ÌĪ
    0.07
    dür
    0.07
    idget
    0.06
    Activations Density 0.105%

    No Known Activations