© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28822
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or references related to statistics and counts

    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
    ekil
    -0.08
    istrovstvÃŃ
    -0.07
    ÑģÑĤÑİ
    -0.07
    uebas
    -0.07
    lassen
    -0.07
    adian
    -0.07
    seau
    -0.07
    ==$
    -0.07
    úsqueda
    -0.07
    lobs
    -0.07
    POSITIVE LOGITS
    ledged
    0.07
    ByKey
    0.07
    /count
    0.06
    enance
    0.06
     count
    0.06
    amik
    0.06
     registered
    0.06
    scale
    0.06
    oring
    0.06
    agle
    0.06
    Activations Density 0.003%

    No Known Activations