© 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. 129612
    Prev
    Next
    INDEX
    Explanations

    words related to becoming

    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
    bilt
    -0.08
    rede
    -0.07
    CreateInfo
    -0.07
    onn
    -0.07
    à¹ģà¸Ĥ
    -0.06
    295
    -0.06
    roof
    -0.06
    laps
    -0.06
    jekt
    -0.06
    COND
    -0.06
    POSITIVE LOGITS
    ibase
    0.08
    ing
    0.08
    levance
    0.07
    æ®ĸ
    0.07
    chw
    0.07
    nown
    0.07
    oming
    0.06
    erc
    0.06
    ulario
    0.06
    TING
    0.06
    Activations Density 0.004%

    No Known Activations