Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 8-LLAMASCOPE-RES-32K
    6. 22726
    Prev
    Next
    INDEX
    Explanations

    references to sources or acknowledgments in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [array
    -0.15
    kol
    -0.15
    kad
    -0.15
    lets
    -0.14
    jang
    -0.14
    zd
    -0.13
    working
    -0.13
    abouts
    -0.13
    acio
    -0.13
    audi
    -0.13
    POSITIVE LOGITS
    alsa
    0.17
    699
    0.16
    onec
    0.15
    sey
    0.15
    877
    0.15
    721
    0.15
    amt
    0.14
    753
    0.14
    939
    0.14
    cola
    0.14
    Activations Density 0.007%

    No Known Activations