© 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. 54940
    Prev
    Next
    INDEX
    Explanations

    terms related to absorption and filtering processes

    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
    asn
    -0.06
    ño
    -0.06
     appare
    -0.06
     putas
    -0.06
    ASM
    -0.06
    etu
    -0.06
    èľ
    -0.06
     cán
    -0.06
    allis
    -0.06
     ==(
    -0.06
    POSITIVE LOGITS
     excess
    0.08
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.07
     harmful
    0.07
     ads
    0.06
    ington
    0.06
     abs
    0.06
     absorption
    0.06
     Toolkit
    0.06
     dro
    0.06
    oust
    0.06
    Activations Density 0.011%

    No Known Activations