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. 10-LLAMASCOPE-RES-32K
    6. 11231
    Prev
    Next
    INDEX
    Explanations

    specific brand names and music-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iro
    -0.17
    osate
    -0.17
    isque
    -0.14
     rencont
    -0.14
    ç©´
    -0.14
    oloj
    -0.13
    Ìģt
    -0.13
    antro
    -0.13
     Kerr
    -0.13
    phies
    -0.13
    POSITIVE LOGITS
    ovich
    0.13
    erland
    0.13
    ream
    0.13
    enburg
    0.13
    786
    0.13
    CEF
    0.13
    heimer
    0.13
    iston
    0.12
    inson
    0.12
    Horizontal
    0.12
    Activations Density 0.703%

    No Known Activations