© 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. 3237
    Prev
    Next
    INDEX
    Explanations

    references to fame and recognition in the context of individuals

    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
    urus
    -0.07
    ocha
    -0.07
    onus
    -0.07
    oni
    -0.06
    onia
    -0.06
    .mix
    -0.06
    atego
    -0.06
    idot
    -0.06
    init
    -0.06
    ãĥ¥
    -0.06
    POSITIVE LOGITS
     remembered
    0.11
     known
    0.11
     most
    0.10
    known
    0.10
     bekannt
    0.09
     Known
    0.09
    Known
    0.09
     familiar
    0.08
     best
    0.08
     MOST
    0.08
    Activations Density 0.064%

    No Known Activations