© 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. 88058
    Prev
    Next
    INDEX
    Explanations

    references to paragraphs or the structural organization of text

    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
     hod
    -0.08
    QueryBuilder
    -0.07
    773
    -0.07
    iyel
    -0.06
    LEC
    -0.06
    DD
    -0.06
    combe
    -0.06
    uft
    -0.06
    äter
    -0.06
    burn
    -0.06
    POSITIVE LOGITS
    -long
    0.10
    arians
    0.09
    naire
    0.09
    swith
    0.07
    arian
    0.07
    -level
    0.07
    ures
    0.07
    mith
    0.07
    ettes
    0.07
    ucch
    0.07
    Activations Density 0.003%

    No Known Activations