© 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. 96105
    Prev
    Next
    INDEX
    Explanations

    phrases related to forward-looking or proactive statements

    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
    eref
    -0.07
     Pais
    -0.07
    371
    -0.06
    ине
    -0.06
    askell
    -0.06
    -HT
    -0.06
    ulse
    -0.06
    ç·Ĵ
    -0.06
    kr
    -0.06
    Å¡t
    -0.06
    POSITIVE LOGITS
     forward
    0.09
    /back
    0.09
    -forward
    0.08
    age
    0.08
     thrust
    0.08
    Forward
    0.08
    forward
    0.07
     Forward
    0.07
    ARSE
    0.07
    anche
    0.07
    Activations Density 0.010%

    No Known Activations