© 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. 58404
    Prev
    Next
    INDEX
    Explanations

    references to the birth of children or news about babies

    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
    ICODE
    -0.08
    ROTO
    -0.08
    ignum
    -0.07
    Ｉ
    -0.07
    alloween
    -0.07
    ipers
    -0.07
    ventus
    -0.07
    asiswa
    -0.07
    issors
    -0.07
    Ìģc
    -0.07
    POSITIVE LOGITS
    itta
    0.06
    nah
    0.06
     Alv
    0.05
     Toro
    0.05
     Bry
    0.05
    ÑĮе
    0.05
     bosses
    0.05
     Cheat
    0.05
    \u
    0.05
    alg
    0.05
    Activations Density 0.007%

    No Known Activations