Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 28382
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "extract" and its synonyms related to obtaining substances or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ais
    -0.16
    IDS
    -0.15
    clazz
    -0.14
     Choices
    -0.14
     shepherd
    -0.14
    ned
    -0.14
    à¸Ķร
    -0.14
     spor
    -0.14
    467
    -0.14
    etr
    -0.14
    POSITIVE LOGITS
    ivism
    0.17
     ÙħÙĨÙĩ
    0.17
    ãĥ¬ãĥĥãĥĪ
    0.17
    ors
    0.16
    ivist
    0.15
    æİ
    0.15
    LLL
    0.14
     from
    0.14
     ÙħÙĨÙĩا
    0.14
    iego
    0.14
    Activations Density 0.040%

    No Known Activations