© 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. 28453
    Prev
    Next
    INDEX
    Explanations

    elements related to reader engagement and emotional connection with characters

    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
    ì¶ľ
    -0.07
    .compress
    -0.06
    qv
    -0.06
     adher
    -0.06
    é³´
    -0.06
    çĽĺ
    -0.06
    _bitmap
    -0.06
     Filed
    -0.06
    벨
    -0.06
    /we
    -0.05
    POSITIVE LOGITS
     reading
    0.24
     Reading
    0.19
     reads
    0.19
     read
    0.19
    reading
    0.18
    Reading
    0.18
    读
    0.18
    éĺħ读
    0.18
    -read
    0.17
    èªŃ
    0.16
    Activations Density 0.163%

    No Known Activations