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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98755
    Prev
    Next
    INDEX
    Explanations

    parentheses and degree indicators in educational qualifications

    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
    oha
    -0.06
    orough
    -0.06
    gend
    -0.06
     Wright
    -0.06
    gra
    -0.05
    rens
    -0.05
    ãģŁ
    -0.05
    .provider
    -0.05
    ilet
    -0.05
    bows
    -0.05
    POSITIVE LOGITS
    Barrier
    0.07
    ë³
    0.07
     Wilde
    0.07
     <$
    0.07
    Ïģιν
    0.07
    tru
    0.07
    _mD
    0.07
    ÑĤÑİ
    0.07
    ’ÑĶ
    0.07
    }elseif
    0.07
    Activations Density 0.005%

    No Known Activations