© 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. 71865
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially periods

    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
    oz
    -0.07
    ULLET
    -0.06
    hd
    -0.06
    oro
    -0.06
    oo
    -0.06
    ig
    -0.05
     blitz
    -0.05
    ``↵
    -0.05
    oe
    -0.05
    ht
    -0.05
    POSITIVE LOGITS
    aname
    0.08
    sonian
    0.08
    criptor
    0.08
    shima
    0.08
    sov
    0.07
    ÑĤаÑĢ
    0.07
    mong
    0.07
    MDB
    0.07
    oland
    0.07
    าà¸Ļà¸Ħร
    0.07
    Activations Density 0.007%

    No Known Activations