© 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. 93648
    Prev
    Next
    INDEX
    Explanations

    references to accountability and public image in sports contexts

    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
    &m
    -0.08
    ramer
    -0.07
     folks
    -0.07
    ekim
    -0.07
     ApiException
    -0.07
    ekler
    -0.07
    ibold
    -0.07
     bü
    -0.07
    agh
    -0.07
     Binder
    -0.07
    POSITIVE LOGITS
    -
    0.06
    uve
    0.06
    rosse
    0.06
    ÅĽnie
    0.06
     Borders
    0.06
    essor
    0.06
     cushions
    0.06
    gae
    0.06
    holm
    0.06
     Scri
    0.06
    Activations Density 0.009%

    No Known Activations