© 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 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. 130952
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating addition or affirmation

    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
    ote
    -0.07
    otes
    -0.06
    idd
    -0.06
    /or
    -0.06
    and
    -0.06
    und
    -0.06
     eb
    -0.06
     Educ
    -0.06
    etc
    -0.06
     æĽ
    -0.06
    POSITIVE LOGITS
     gonna
    0.10
     supposed
    0.08
    rame
    0.08
    iesen
    0.07
     ours
    0.07
     suppose
    0.07
     taken
    0.07
    going
    0.07
    rint
    0.07
     able
    0.07
    Activations Density 0.257%

    No Known Activations