© 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. 29-LLAMASCOPE-RES-32K
    11. 14099
    Prev
    Next
    INDEX
    Explanations

    references to personal accomplishments and participatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fifty
    -0.20
     Forty
    -0.18
     Hundred
    -0.17
     Thirty
    -0.16
     twentieth
    -0.16
    Thirty
    -0.15
     Sevent
    -0.14
    ovky
    -0.14
     Nin
    -0.14
    illions
    -0.13
    POSITIVE LOGITS
     three
    0.94
     four
    0.93
     five
    0.88
     six
    0.85
     seven
    0.79
     two
    0.78
     eight
    0.75
    three
    0.73
     nine
    0.67
    five
    0.66
    Activations Density 2.826%

    No Known Activations