© 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. 84419
    Prev
    Next
    INDEX
    Explanations

    references to geometric shapes and their properties

    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
    Fcn
    -0.08
    \views
    -0.07
    ritel
    -0.07
     ÐľÑĸнÑĸÑģÑĤ
    -0.07
    541
    -0.07
    :č↵č↵
    -0.06
    ILTER
    -0.06
    BufferData
    -0.06
    «ĺ
    -0.06
    ãĥ©ãĥ³ãĤ¹
    -0.06
    POSITIVE LOGITS
     Bernardino
    0.07
    onso
    0.06
    noinspection
    0.06
    \-
    0.06
     Prairie
    0.06
    éli
    0.05
     DESCRIPTION
    0.05
    enzhen
    0.05
    etÃł
    0.05
    olecules
    0.05
    Activations Density 0.027%

    No Known Activations