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. 5-LLAMASCOPE-RES-32K
    6. 18521
    Prev
    Next
    INDEX
    Explanations

    coding elements related to Python imports and file handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouser
    -0.16
    reopen
    -0.14
    оÑģÑĮ
    -0.14
    athe
    -0.14
    outu
    -0.14
     tents
    -0.13
    ingen
    -0.13
    hdr
    -0.13
    ycz
    -0.13
    ething
    -0.13
    POSITIVE LOGITS
    cher
    0.16
    онд
    0.14
    oca
    0.14
    êt
    0.14
    atore
    0.13
     Laden
    0.13
    816
    0.13
    ê
    0.13
    ä¸ĢæŃ¥
    0.13
     labour
    0.13
    Activations Density 0.032%

    No Known Activations