© 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. 29787
    Prev
    Next
    INDEX
    Explanations

    the letter "h"

    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
     parc
    -0.07
    uthor
    -0.07
    -bs
    -0.07
    abase
    -0.07
    idar
    -0.07
    assed
    -0.06
    å¥Ī
    -0.06
    ãĤ¹ãĥ¬
    -0.06
    çĿ
    -0.06
    izmet
    -0.06
    POSITIVE LOGITS
    utation
    0.06
    unter
    0.05
    umi
    0.05
    åį
    0.05
     obviously
    0.05
     ("
    0.05
    ches
    0.05
    (jq
    0.05
    alem
    0.05
    conda
    0.05
    Activations Density 0.000%

    No Known Activations