© 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. 22-LLAMASCOPE-RES-131K
    6. 3759
    Prev
    Next
    INDEX
    Explanations

    connective phrases and logical transitions in reasoning

    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
    jee
    -0.09
    DESCRIPTION
    -0.08
    peater
    -0.07
    amoto
    -0.07
    zac
    -0.07
    ýn
    -0.07
    ephir
    -0.07
    olly
    -0.07
    еÑĢеж
    -0.07
    üstü
    -0.07
    POSITIVE LOGITS
     let
    0.07
     majority
    0.07
     even
    0.07
    unk
    0.06
    even
    0.06
     Let
    0.06
    let
    0.06
     remember
    0.06
    äºŃ
    0.06
     unknow
    0.06
    Activations Density 0.015%

    No Known Activations