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. 29-LLAMASCOPE-RES-32K
    6. 17527
    Prev
    Next
    INDEX
    Explanations

    coding and markup elements relevant to web development

    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
    ificate
    -0.16
    ì¹Ń
    -0.15
    lef
    -0.15
    laden
    -0.15
    سÛĮÙĨ
    -0.15
    :CGRect
    -0.14
    -toast
    -0.14
    _MODAL
    -0.14
    locker
    -0.14
    γÏīν
    -0.14
    POSITIVE LOGITS
     li
    0.47
     ul
    0.44
     bullet
    0.43
     Bullet
    0.42
    li
    0.41
    Bullet
    0.39
     bullets
    0.37
    -li
    0.37
     Ul
    0.37
    ul
    0.36
    Activations Density 0.066%

    No Known Activations