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. 16920
    Prev
    Next
    INDEX
    Explanations

    phrases indicating results from research studies or scientific findings

    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
    itar
    -0.16
    κά
    -0.15
    abe
    -0.14
    ihn
    -0.14
    ettel
    -0.14
    938
    -0.13
    910
    -0.13
    723
    -0.13
    utenberg
    -0.12
     внеÑģ
    -0.12
    POSITIVE LOGITS
     findings
    0.81
     results
    0.74
    results
    0.60
     finding
    0.60
     Find
    0.57
    find
    0.56
     Results
    0.56
     finds
    0.55
    -find
    0.54
     find
    0.52
    Activations Density 0.253%

    No Known Activations