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. 10-LLAMASCOPE-RES-32K
    6. 3855
    Prev
    Next
    INDEX
    Explanations

    chapter and section headings in a structured document

    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
    .proc
    -0.16
     Og
    -0.15
    rock
    -0.14
    åĿĤ
    -0.14
    ãĥ¬ãĥĥãĥĪ
    -0.14
    iska
    -0.14
    ahan
    -0.13
    ust
    -0.13
    aghan
    -0.13
    åĭ¤
    -0.13
    POSITIVE LOGITS
    adoo
    0.16
    UNET
    0.14
     Ned
    0.14
     unh
    0.14
    eparator
    0.14
     Bios
    0.14
    aname
    0.14
    stad
    0.14
    raquo
    0.14
    _mx
    0.14
    Activations Density 0.028%

    No Known Activations