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. 7-LLAMASCOPE-RES-32K
    6. 6276
    Prev
    Next
    INDEX
    Explanations

    references to characters, series, and events in popular TV shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wart
    -0.16
    atron
    -0.15
    iat
    -0.15
    spe
    -0.15
    ç
    -0.14
    eam
    -0.14
     kup
    -0.14
    HeaderValue
    -0.14
    å°Ĥ
    -0.14
    dera
    -0.14
    POSITIVE LOGITS
    Ware
    0.17
     Ware
    0.15
    THON
    0.15
    ÑĦÑĸ
    0.15
     redistribution
    0.14
    ëĭ¬
    0.14
    bourg
    0.14
     Rack
    0.14
    431
    0.14
     ENG
    0.14
    Activations Density 0.010%

    No Known Activations