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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125451
    Prev
    Next
    INDEX
    Explanations

    academic citations and affiliations

    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
    гов
    -0.07
    apiro
    -0.06
     Society
    -0.06
     Gaines
    -0.06
    каж
    -0.06
    isoft
    -0.06
     Disp
    -0.05
    erne
    -0.05
    ÄĽ
    -0.05
    cors
    -0.05
    POSITIVE LOGITS
    ãģ¬
    0.07
     STRICT
    0.07
    drž
    0.07
    buckets
    0.06
    ÐĶÐļ
    0.06
    à¥ĭà¥ľ
    0.06
    tuk
    0.06
     promot
    0.06
     Uhr
    0.06
    otel
    0.06
    Activations Density 0.043%

    No Known Activations