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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 26-LLAMASCOPE-RES-32K
    6. 1553
    Prev
    Next
    INDEX
    Explanations

    references to ocean-related topics or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تج
    -0.16
    lep
    -0.16
    aday
    -0.16
    erez
    -0.15
    lez
    -0.15
    bert
    -0.15
    sit
    -0.15
    arem
    -0.15
    lef
    -0.15
    æĮ¯ãĤĬ
    -0.14
    POSITIVE LOGITS
    ic
    0.39
    front
    0.32
    ographic
    0.29
    ographers
    0.26
    ographer
    0.24
    ography
    0.23
    -going
    0.23
    arium
    0.23
    ics
    0.22
    wide
    0.20
    Activations Density 0.008%

    No Known Activations