© 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. 9-LLAMASCOPE-RES-131K
    6. 95748
    Prev
    Next
    INDEX
    Explanations

    occurrences of 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
    inee
    -0.06
    nech
    -0.06
    option
    -0.06
    ie
    -0.06
    ë¦Ħ
    -0.06
     Miscellaneous
    -0.05
    oples
    -0.05
    band
    -0.05
    aves
    -0.05
    Co
    -0.05
    POSITIVE LOGITS
    ãĤ¤ãĥĦ
    0.08
    CharCode
    0.07
    istrat
    0.07
    UILTIN
    0.07
    StateException
    0.07
    .SDK
    0.07
    MLElement
    0.07
    oux
    0.07
    รà¸ģ
    0.07
    RunWith
    0.06
    Activations Density 0.000%

    No Known Activations