© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 63085
    Prev
    Next
    INDEX
    Explanations

    references to the concept of survival in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ion
    -0.08
    acht
    -0.08
    wen
    -0.06
    ION
    -0.06
    alle
    -0.06
    awa
    -0.06
     afs
    -0.06
    ree
    -0.06
    atsu
    -0.06
    unting
    -0.06
    POSITIVE LOGITS
    ROTO
    0.09
    .scalablytyped
    0.08
    DataExchange
    0.08
    CustomLabel
    0.07
    endance
    0.07
    /live
    0.07
     surv
    0.07
    ÑģÑĮого
    0.07
    /win
    0.07
    -toggler
    0.07
    Activations Density 0.014%

    No Known Activations