© 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. 74292
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to evaluations or comparisons of characters and their roles in a narrative context

    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
     versus
    -0.06
     vs
    -0.06
    _rb
    -0.06
    еÑģи
    -0.06
    enties
    -0.06
    vs
    -0.06
    ystate
    -0.06
    xed
    -0.06
    çĶ
    -0.06
     ____
    -0.06
    POSITIVE LOGITS
     alike
    0.08
    .scalablytyped
    0.07
     sheer
    0.06
    ahlen
    0.06
    缸åIJĮ
    0.06
    Æ
    0.06
    BJECT
    0.06
    ADIUS
    0.06
    ryn
    0.06
     Ñģло
    0.06
    Activations Density 0.027%

    No Known Activations