© 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. 28920
    Prev
    Next
    INDEX
    Explanations

    monetary values and associated numerical data

    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
    663
    -0.07
    orch
    -0.06
    ãĥ¼ãĥĸãĥ«
    -0.06
    enge
    -0.06
    301
    -0.06
    ewan
    -0.06
    BackingField
    -0.06
    erson
    -0.06
    UIAlertAction
    -0.06
    alties
    -0.06
    POSITIVE LOGITS
    #ad
    0.07
    ãĥªãĥ³ãĤ°
    0.07
    ÄįÃŃ
    0.07
    .Actions
    0.07
    luž
    0.06
    _TC
    0.06
    ugen
    0.06
    CASE
    0.06
    SENS
    0.06
    vell
    0.06
    Activations Density 0.011%

    No Known Activations