© 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 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. 17-LLAMASCOPE-RES-131K
    11. 78512
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate assistive actions and support

    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
     while
    -0.07
     whereas
    -0.07
     gratuitement
    -0.07
    arena
    -0.06
    nat
    -0.06
    ellij
    -0.06
    ftp
    -0.06
     notamment
    -0.06
    while
    -0.06
    ersen
    -0.06
    POSITIVE LOGITS
     always
    0.12
    always
    0.11
     ALWAYS
    0.10
    Always
    0.10
     siempre
    0.10
     vždy
    0.10
     Always
    0.10
     вÑģегда
    0.09
     Äijá»ģu
    0.09
     sempre
    0.09
    Activations Density 0.044%

    No Known Activations