© 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. 42599
    Prev
    Next
    INDEX
    Explanations

    pronouns that indicate possession and self-reference

    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
    ä½łä»¬
    -0.07
     teil
    -0.07
    SED
    -0.07
     yourselves
    -0.07
    ois
    -0.07
    åĪ¶åº¦
    -0.07
    ÎłÎij
    -0.07
    ols
    -0.07
    inely
    -0.07
    EXTERN
    -0.07
    POSITIVE LOGITS
    (s
    0.07
    /he
    0.06
    umba
    0.06
    esus
    0.06
     reliably
    0.06
    Ì
    0.06
     Browse
    0.06
    us
    0.06
    on
    0.06
    ismatch
    0.06
    Activations Density 0.038%

    No Known Activations