© 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. 125714
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation, particularly quotation 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
    éments
    -0.08
    .dm
    -0.07
    éĹ´
    -0.07
    igans
    -0.07
    .googleapis
    -0.07
    HWND
    -0.07
    ffset
    -0.07
    erson
    -0.07
    ees
    -0.07
    raz
    -0.07
    POSITIVE LOGITS
    ingu
    0.06
    ir
    0.06
    UNCH
    0.06
    atif
    0.06
    292
    0.06
     typical
    0.06
    igator
    0.05
    ilip
    0.05
     Mund
    0.05
    conditionally
    0.05
    Activations Density 0.014%

    No Known Activations