© 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. 17112
    Prev
    Next
    INDEX
    Explanations

    statements and messages surrounding events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    A colon preceding quoted text, typically introducing a formal statement, email, letter, or other direct communication.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    plus
    -0.06
    alley
    -0.06
    Plus
    -0.06
    igi
    -0.06
    ion
    -0.05
     hyp
    -0.05
     Plus
    -0.05
    ner
    -0.05
    führt
    -0.05
    oph
    -0.05
    POSITIVE LOGITS
    Dear
    0.11
     Dear
    0.11
     dear
    0.10
    viso
    0.08
    ãĤ«ãĥĨãĤ´ãĥª
    0.07
    bek
    0.07
    Attachments
    0.07
    аÑĢÑĩ
    0.07
    ikut
    0.07
    reetings
    0.07
    Activations Density 0.021%

    No Known Activations