© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15108
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related references in the text

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Calder
    -0.07
    ellij
    -0.07
    gon
    -0.07
    ideon
    -0.07
    icens
    -0.07
    uracy
    -0.07
    arts
    -0.07
    enden
    -0.06
     Ñĥз
    -0.06
    odelist
    -0.06
    POSITIVE LOGITS
     fault
    0.09
     Fault
    0.09
    fault
    0.08
     undo
    0.07
    Ìĥ
    0.07
    Fault
    0.07
    opsy
    0.07
     Achilles
    0.07
     cue
    0.06
     norm
    0.06
    Activations Density 0.030%

    No Known Activations