© 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. 22-LLAMASCOPE-RES-131K
    11. 3838
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in code or written text

    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
    .INSTANCE
    -0.08
    gend
    -0.08
    ãĥĭãĥĥãĤ¯
    -0.07
    agan
    -0.07
     пÑĢоÑĤи
    -0.07
    phan
    -0.07
    <<<<<<<<
    -0.07
    inks
    -0.07
    ıl
    -0.07
    seau
    -0.07
    POSITIVE LOGITS
     public
    0.06
     particular
    0.06
    aju
    0.06
     certain
    0.05
     however
    0.05
    lasting
    0.05
     Hover
    0.05
     especially
    0.05
    amaha
    0.05
     per
    0.05
    Activations Density 0.001%

    No Known Activations