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. 7-LLAMASCOPE-RES-32K
    6. 7782
    Prev
    Next
    INDEX
    Explanations

    names of fairy tale characters and references to fairy tales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outh
    -0.15
    uro
    -0.15
    ant
    -0.15
    747
    -0.15
    ount
    -0.14
    tz
    -0.14
    rc
    -0.14
    o
    -0.14
    anta
    -0.14
    543
    -0.14
    POSITIVE LOGITS
    ompiler
    0.17
    รà¸Ńà¸ĩ
    0.17
    çħ§
    0.16
    átek
    0.15
    CLUD
    0.15
    ħn
    0.15
    èĢIJ
    0.14
    оки
    0.14
    LOCKS
    0.14
    owi
    0.14
    Activations Density 0.019%

    No Known Activations