© 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 EvalsExportsAPI 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. 82974
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns and possessive forms of "he" and "his."

    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
    reeNode
    -0.08
     ogs
    -0.07
    omik
    -0.07
    lasses
    -0.07
    ¶Į
    -0.07
    eln
    -0.07
    ковÑĸ
    -0.07
    евид
    -0.07
    ertainment
    -0.07
    usercontent
    -0.07
    POSITIVE LOGITS
     or
    0.10
    /her
    0.08
    /she
    0.06
    onom
    0.06
    彼女
    0.06
    (.)
    0.06
     sil
    0.06
     she
    0.06
    yo
    0.06
    osph
    0.06
    Activations Density 0.004%

    No Known Activations