© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 8564
    Prev
    Next
    INDEX
    Explanations

    patterns of consistency and similarity in systems or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     separate
    -0.15
    à¹Ģà¸Ł
    -0.14
    jac
    -0.14
     Beng
    -0.14
    ipa
    -0.14
     separately
    -0.14
     Beard
    -0.13
    ew
    -0.13
     double
    -0.13
    ance
    -0.13
    POSITIVE LOGITS
     identical
    0.40
     uniform
    0.40
    缸åIJĮ
    0.32
    Uniform
    0.32
    uniform
    0.31
     Uniform
    0.30
     ident
    0.28
     ëıĻìĿ¼
    0.27
    _same
    0.26
     alike
    0.25
    Activations Density 0.261%

    No Known Activations