© 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. 81002
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and adjectives

    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
    etine
    -0.08
     geil
    -0.07
    killer
    -0.07
    ainless
    -0.07
    .RunWith
    -0.07
    amt
    -0.07
    acente
    -0.07
    ienen
    -0.07
    inne
    -0.07
    formance
    -0.07
    POSITIVE LOGITS
     own
    0.10
     OWN
    0.08
     mark
    0.07
     Own
    0.07
    SELF
    0.06
    sel
    0.06
     brit
    0.06
    sie
    0.06
     o
    0.06
     way
    0.06
    Activations Density 0.053%

    No Known Activations