© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87326
    Prev
    Next
    INDEX
    Explanations

    phrases related to entertaining or adult-themed content

    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
    uler
    -0.07
    udder
    -0.07
    AYS
    -0.06
    atron
    -0.06
    ULER
    -0.06
    ò
    -0.06
     Anders
    -0.06
    _DST
    -0.06
    inci
    -0.06
    venues
    -0.06
    POSITIVE LOGITS
     Laur
    0.06
    inality
    0.06
     Medium
    0.06
     flaw
    0.06
    emachine
    0.06
     voks
    0.06
     partially
    0.06
     Wayback
    0.06
    ermo
    0.06
    asting
    0.06
    Activations Density 0.001%

    No Known Activations