© 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. 17-LLAMASCOPE-RES-131K
    11. 4863
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and variations of "do not" phrases

    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
    osu
    -0.07
    ascus
    -0.07
    .mods
    -0.07
    avana
    -0.07
    ouro
    -0.07
    ÃĹ↵↵
    -0.06
    ilst
    -0.06
    sip
    -0.06
    allet
    -0.06
    aines
    -0.06
    POSITIVE LOGITS
    azio
    0.06
    ãĥ£
    0.06
    odes
    0.06
    etta
    0.06
    izen
    0.06
    SETS
    0.05
    ÙĬع
    0.05
     fashion
    0.05
    anza
    0.05
    åijĬ
    0.05
    Activations Density 0.000%

    No Known Activations