© 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. 103851
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns and modal verbs indicating necessity or potential actions

    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
    asca
    -0.09
    ebin
    -0.09
    $MESS
    -0.08
    ikler
    -0.08
    eon
    -0.08
    ãİ
    -0.08
    ekim
    -0.07
     dilig
    -0.07
    çĨ
    -0.07
    ково
    -0.07
    POSITIVE LOGITS
     must
    0.13
     Must
    0.12
    must
    0.11
    Must
    0.10
    å¿ħé¡»
    0.09
     needs
    0.08
     MUST
    0.08
     å¿ħ
    0.08
     requires
    0.08
     need
    0.08
    Activations Density 0.023%

    No Known Activations