© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4101
    Prev
    Next
    INDEX
    Explanations

    instances of the word "select" and its variations related to choice or selection processes

    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
    adden
    -0.06
    usb
    -0.06
    sv
    -0.06
    ãĥ«ãĥī
    -0.06
     Rank
    -0.06
     secre
    -0.06
    ister
    -0.06
    -green
    -0.05
    ste
    -0.05
    æĨ
    -0.05
    POSITIVE LOGITS
    æĬŀ
    0.08
    æĬľ
    0.07
    ivity
    0.07
    551
    0.07
     lá»įc
    0.07
    BYTES
    0.07
    ignet
    0.07
    SingleNode
    0.07
    oked
    0.07
    ivec
    0.07
    Activations Density 0.009%

    No Known Activations