© 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. 5-LLAMASCOPE-RES-131K
    11. 126498
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "treasure trove."

    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
    acer
    -0.07
    rowable
    -0.06
    359
    -0.06
    ,'#
    -0.06
    897
    -0.06
    arer
    -0.06
    wer
    -0.06
    phan
    -0.06
    x
    -0.06
    avana
    -0.06
    POSITIVE LOGITS
    ardy
    0.07
    ckill
    0.07
    Fuse
    0.07
    eler
    0.07
    /array
    0.06
    plr
    0.06
    opc
    0.06
    uÅŁ
    0.06
    isclosed
    0.06
    ChangeEvent
    0.06
    Activations Density 0.003%

    No Known Activations