© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87198
    Prev
    Next
    INDEX
    Explanations

    phrases related to current information or updates

    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
    //{{
    -0.08
    .nextSibling
    -0.07
    _Settings
    -0.07
     enter
    -0.07
    096
    -0.07
     Ludwig
    -0.07
    .MixedReality
    -0.07
    ekli
    -0.07
     Cousins
    -0.06
    OTES
    -0.06
    POSITIVE LOGITS
     off
    0.06
    ÃŃt
    0.06
    atch
    0.06
    sah
    0.06
    peg
    0.06
    les
    0.06
    afone
    0.06
     ëĸ
    0.05
    VEL
    0.05
    esen
    0.05
    Activations Density 0.000%

    No Known Activations