© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127313
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation, particularly periods, within the text

    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
     tre
    -0.06
    yk
    -0.06
     also
    -0.06
    ÑĢÑĥг
    -0.06
    sen
    -0.06
    临
    -0.06
    eb
    -0.06
     naturally
    -0.05
     bulk
    -0.05
    kup
    -0.05
    POSITIVE LOGITS
    _capability
    0.08
     maybe
    0.08
    BOTTOM
    0.08
    rzy
    0.08
    arov
    0.07
    .Done
    0.07
     hopefully
    0.07
    amet
    0.07
     Hopefully
    0.07
    -ves
    0.07
    Activations Density 0.016%

    No Known Activations