© 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. 3199
    Prev
    Next
    INDEX
    Explanations

    timestamps and date-related information

    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
     spole
    -0.08
    arent
    -0.07
    aring
    -0.07
    ibling
    -0.07
    ides
    -0.07
    blogs
    -0.07
    ibia
    -0.07
    resco
    -0.06
    etrics
    -0.06
    ival
    -0.06
    POSITIVE LOGITS
    ertz
    0.07
    uppen
    0.06
    ABCDEFGHI
    0.06
     ÄĮech
    0.06
    eprom
    0.06
     Laugh
    0.06
     Chow
    0.06
    ноп
    0.06
    DDL
    0.06
    _soc
    0.06
    Activations Density 0.009%

    No Known Activations