© 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. 21-LLAMASCOPE-RES-32K
    11. 8107
    Prev
    Next
    INDEX
    Explanations

    structured lists and descriptions of collective entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     both
    -0.26
     Both
    -0.22
    Both
    -0.22
    both
    -0.22
     BOTH
    -0.20
     beide
    -0.20
     third
    -0.17
    tring
    -0.17
    _both
    -0.16
    両
    -0.16
    POSITIVE LOGITS
     four
    0.56
     five
    0.52
    five
    0.46
     six
    0.45
     seven
    0.43
    four
    0.41
     bá»ijn
    0.41
     eight
    0.40
     ÑĩеÑĤÑĭ
    0.39
     cuatro
    0.38
    Activations Density 0.184%

    No Known Activations