© 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. 120184
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related references indicating ownership or association

    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
    оваÑĢ
    -0.07
     somebody
    -0.07
    ahoo
    -0.07
    ÃŃÅĻ
    -0.07
    embros
    -0.07
    elerinden
    -0.06
    mamak
    -0.06
     докÑĥм
    -0.06
    øj
    -0.06
    uelles
    -0.06
    POSITIVE LOGITS
     focus
    0.09
     attention
    0.09
     attent
    0.08
     energies
    0.08
    attention
    0.08
    focus
    0.07
     ire
    0.07
     effort
    0.07
     efforts
    0.07
     sights
    0.07
    Activations Density 0.011%

    No Known Activations