© 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. 9-LLAMASCOPE-RES-131K
    11. 94219
    Prev
    Next
    INDEX
    Explanations

    the phrase "in" and related contextual indicators of condition and situation

    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
    elli
    -0.07
    anova
    -0.06
    \Mapping
    -0.06
    com
    -0.06
    irus
    -0.06
    _SUR
    -0.06
    bow
    -0.06
    anke
    -0.06
     Surv
    -0.06
    dress
    -0.06
    POSITIVE LOGITS
    afs
    0.07
    çĶ²
    0.07
    mue
    0.07
    ASTER
    0.06
    .hm
    0.06
     repost
    0.06
    pecified
    0.06
    elen
    0.06
    .nr
    0.06
    .struct
    0.06
    Activations Density 0.000%

    No Known Activations