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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 19934
    Prev
    Next
    INDEX
    Explanations

    equations and mathematical notation

    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
    urette
    -0.21
    ãģ°ãģĭãĤĬ
    -0.15
     æ¼
    -0.14
    виÑĤ
    -0.14
    дÑı
    -0.13
    æ°ĹãģĮ
    -0.13
    .easing
    -0.12
    DDD
    -0.12
     ÐĴики
    -0.12
    rieve
    -0.12
    POSITIVE LOGITS
    eted
    0.15
    NotAllowed
    0.14
    áÄį
    0.14
    NEWS
    0.14
    _REF
    0.14
    ï¸ı
    0.13
    _bed
    0.12
    ÏĮδ
    0.12
    ĭ
    0.12
    ÄįnÃŃ
    0.12
    Activations Density 0.157%

    No Known Activations