© 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. 81001
    Prev
    Next
    INDEX
    Explanations

    expressions that indicate explanations or reasons behind phenomena

    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
    orget
    -0.07
    essional
    -0.06
    ccb
    -0.06
    èķ
    -0.06
    Ñħови
    -0.06
    ùi
    -0.06
    ella
    -0.06
    taj
    -0.06
    dio
    -0.06
    iddi
    -0.06
    POSITIVE LOGITS
     answer
    0.35
     Answer
    0.30
     answered
    0.29
    answer
    0.28
     answers
    0.28
    çŃĶæ¡Ī
    0.27
     ANSW
    0.26
    Answer
    0.25
     answering
    0.25
    -answer
    0.24
    Activations Density 0.107%

    No Known Activations