© 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. 128979
    Prev
    Next
    INDEX
    Explanations

    characters and identifiers used in programming code

    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
    -vous
    -0.08
    gether
    -0.07
    folio
    -0.07
    edback
    -0.07
    php
    -0.07
    heid
    -0.07
    ation
    -0.07
     sclerosis
    -0.07
    borough
    -0.07
     latter
    -0.07
    POSITIVE LOGITS
    bies
    0.08
    eri
    0.08
    ̣
    0.08
    infeld
    0.07
     à¹Ĩ
    0.07
    bie
    0.07
    sense
    0.07
    ||(
    0.07
    oji
    0.07
    oS
    0.07
    Activations Density 0.129%

    No Known Activations