© 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. 119188
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate causation or reasons for issues

    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
    ÙħاÙħ
    -0.07
    eniable
    -0.07
    ìĤ¬ë¬´
    -0.07
    SGlobal
    -0.07
    .twig
    -0.07
    ahan
    -0.07
    .radioButton
    -0.07
    درÛĮ
    -0.07
    _svc
    -0.07
    راÙĨÛĮ
    -0.07
    POSITIVE LOGITS
     respective
    0.08
     respectively
    0.06
     various
    0.06
    ymi
    0.06
    atur
    0.06
     either
    0.06
    els
    0.06
     shrink
    0.06
     clever
    0.06
    aver
    0.06
    Activations Density 0.043%

    No Known Activations