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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125463
    Prev
    Next
    INDEX
    Explanations

    names and titles related to religious figures and clergy

    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
    ingroup
    -0.07
    lyph
    -0.07
    eurs
    -0.07
     reklam
    -0.07
     practical
    -0.06
    ãĥ³ãĥĦ
    -0.06
    ãĥ³ãĥĩ
    -0.06
    ores
    -0.06
    .ExecuteReader
    -0.06
    ONO
    -0.06
    POSITIVE LOGITS
    deaux
    0.06
    osis
    0.06
     Aydın
    0.06
    avit
    0.06
    anka
    0.06
    avia
    0.06
    assis
    0.06
     mes
    0.06
     mÄĽ
    0.06
    .opts
    0.06
    Activations Density 0.010%

    No Known Activations