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

    Neuronpedia

    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. 60124
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to individuals or groups in a community context

    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
    ãĤŃãĥ³ãĤ°
    -0.07
    umba
    -0.07
    oret
    -0.07
    plr
    -0.07
    оÑĢож
    -0.07
    бав
    -0.07
    idas
    -0.07
    lez
    -0.07
    .Obj
    -0.07
    ÏģÏİ
    -0.06
    POSITIVE LOGITS
     بتÙĪاÙĨ
    0.10
     can
    0.09
     pueda
    0.08
    Can
    0.07
     hopefully
    0.07
     можно
    0.07
    can
    0.07
     pued
    0.06
    èĥ½å¤Ł
    0.06
    etas
    0.06
    Activations Density 0.032%

    No Known Activations