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. 5-LLAMASCOPE-RES-32K
    6. 18850
    Prev
    Next
    INDEX
    Explanations

    the opening and closing tags in markup or code structures

    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
    hra
    -0.17
    ÑĮÑİÑĤ
    -0.17
    ustr
    -0.15
    uyla
    -0.15
    chandle
    -0.14
    AccessType
    -0.14
    ìĭ±
    -0.14
    holm
    -0.14
    SED
    -0.14
    nown
    -0.14
    POSITIVE LOGITS
    linger
    0.16
    ally
    0.16
     Lange
    0.15
     Kush
    0.15
    weet
    0.15
     rd
    0.14
     Rein
    0.14
    entry
    0.14
    виÑī
    0.14
     which
    0.14
    Activations Density 0.041%

    No Known Activations