© 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. 9-LLAMASCOPE-RES-131K
    11. 94608
    Prev
    Next
    INDEX
    Explanations

    expressions of reassurance and concern

    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
    aal
    -0.08
    jid
    -0.07
    ucht
    -0.07
    avings
    -0.06
    acher
    -0.06
    yz
    -0.06
    agua
    -0.06
    aan
    -0.06
     Hills
    -0.06
    /gcc
    -0.06
    POSITIVE LOGITS
    iversit
    0.06
    omik
    0.06
    .bn
    0.06
     Serialized
    0.06
    erin
    0.06
    عاد
    0.06
     Lowe
    0.06
    zburg
    0.06
    Ĥ¨
    0.06
     banc
    0.06
    Activations Density 0.010%

    No Known Activations