© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 13731
    Prev
    Next
    INDEX
    Explanations

    technical language related to fluid dynamics and statistical mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rosso
    -0.17
     Ocak
    -0.15
    ugas
    -0.15
     hasil
    -0.15
    ussen
    -0.14
     GObject
    -0.14
     Encore
    -0.14
    à¤Ķ
    -0.14
    simd
    -0.14
    å±Ĭ
    -0.14
    POSITIVE LOGITS
     hum
    0.15
     gen
    0.15
     draining
    0.14
     complimentary
    0.14
     Trev
    0.14
     per
    0.14
    YRO
    0.14
     action
    0.14
     dis
    0.14
    MBER
    0.14
    Activations Density 0.137%

    No Known Activations