© 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. 121096
    Prev
    Next
    INDEX
    Explanations

    phrases related to making comments and engaging in discussions

    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
    mt
    -0.07
     Od
    -0.06
    il
    -0.06
    my
    -0.06
    è¡Ŀ
    -0.06
    adata
    -0.06
    ili
    -0.05
    afi
    -0.05
    iloc
    -0.05
    yer
    -0.05
    POSITIVE LOGITS
    uale
    0.08
    álo
    0.07
    оÑģп
    0.07
    vap
    0.06
     Sexe
    0.06
     UIP
    0.06
    redo
    0.06
    Porno
    0.06
    hle
    0.06
     Timothy
    0.06
    Activations Density 0.001%

    No Known Activations