© 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. 98715
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their use in complex sentences

    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
    imson
    -0.06
    borg
    -0.06
    ÃŁ
    -0.06
    aram
    -0.06
    osph
    -0.06
    aktu
    -0.06
    eling
    -0.06
    ÑĨионалÑĮ
    -0.06
    447
    -0.06
    oppel
    -0.06
    POSITIVE LOGITS
    ÃĹ↵↵
    0.07
    \models
    0.07
    áºŃn
    0.07
     bais
    0.07
    иÑģÑĮ
    0.06
     baise
    0.06
    Äįel
    0.06
    adt
    0.06
    >{@
    0.06
    xcf
    0.06
    Activations Density 0.022%

    No Known Activations