© 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. 84524
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially periods and question marks

    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
    ngen
    -0.06
    ãĤ·ãĥ§ãĥ³
    -0.06
    idor
    -0.06
     kvp
    -0.06
    liable
    -0.06
    rew
    -0.06
     NFC
    -0.05
    -version
    -0.05
    ake
    -0.05
    :NSLocalizedString
    -0.05
    POSITIVE LOGITS
     READ
    0.07
    ©
    0.07
    akk
    0.07
    uki
    0.07
    roma
    0.07
    eyse
    0.06
    ÑĤÑĢо
    0.06
    hma
    0.06
     Magick
    0.06
     VÅ¡ech
    0.06
    Activations Density 0.001%

    No Known Activations