© 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. 11-LLAMASCOPE-RES-32K
    6. 16815
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their specific placements within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jax
    -0.17
    ayas
    -0.16
    undle
    -0.15
    .onCreate
    -0.15
     Goodman
    -0.15
    lix
    -0.14
     landmark
    -0.14
     olmadıģı
    -0.14
    вÑĸд
    -0.14
    ħ§
    -0.14
    POSITIVE LOGITS
    bour
    0.17
    bu
    0.14
    ums
    0.14
    nard
    0.13
    IService
    0.13
     İst
    0.13
     //<
    0.13
     Testament
    0.13
    è¡ĵ
    0.13
    iffe
    0.12
    Activations Density 0.080%

    No Known Activations