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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12476
    Prev
    Next
    INDEX
    Explanations

    repetitive letter patterns and prominent vowel-consonant structures in words

    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
    onne
    -0.17
    ulses
    -0.16
    empre
    -0.15
    verts
    -0.15
    ë¦Ħ
    -0.15
    ì§ĢìļĶ
    -0.15
    ombo
    -0.15
    leyin
    -0.14
    webtoken
    -0.14
    GetObject
    -0.14
    POSITIVE LOGITS
    ization
    0.18
    ical
    0.17
    rap
    0.17
    ating
    0.17
    aim
    0.16
    pch
    0.16
    eme
    0.15
    able
    0.15
    ial
    0.15
    ect
    0.15
    Activations Density 0.171%

    No Known Activations