© 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. 17-LLAMASCOPE-RES-131K
    11. 16890
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Ann."

    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
    folio
    -0.08
    ɵ
    -0.06
    /her
    -0.06
    cul
    -0.06
    .isNullOrEmpty
    -0.05
    Ñģли
    -0.05
     Ñĩего
    -0.05
    .telegram
    -0.05
    cia
    -0.05
     nok
    -0.05
    POSITIVE LOGITS
    upert
    0.08
    pNet
    0.07
    DlgItem
    0.07
    icontrol
    0.07
    prises
    0.07
     showc
    0.07
    eger
    0.07
    ocache
    0.07
     (~(
    0.07
    -instagram
    0.07
    Activations Density 0.005%

    No Known Activations