© 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. 5-LLAMASCOPE-RES-131K
    11. 126111
    Prev
    Next
    INDEX
    Explanations

    articles preceding nouns

    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
    afone
    -0.07
     VÅ¡ech
    -0.06
    redient
    -0.06
    ulfilled
    -0.06
    oster
    -0.06
    ArrayOf
    -0.06
     fray
    -0.06
    rahim
    -0.06
    863
    -0.06
    raid
    -0.06
    POSITIVE LOGITS
    à¥Ģà¤Ľ
    0.07
    ÑģÑĤÑĢи
    0.07
     vá»ijn
    0.07
    SOLE
    0.07
    bara
    0.07
    ÙĨدÙĩ
    0.06
    Ïģιά
    0.06
    Uploader
    0.06
    queda
    0.06
    íij¸
    0.06
    Activations Density 0.030%

    No Known Activations