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

    Neuronpedia

    APICircuit 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. 3224
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and institutions

    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
    Kansas
    -0.32
     Kansas
    -0.32
     Missouri
    -0.24
     Wichita
    -0.23
     Omaha
    -0.23
     Nebraska
    -0.20
     Moines
    -0.20
     Iowa
    -0.20
    ún
    -0.18
     Sioux
    -0.18
    POSITIVE LOGITS
     Tobias
    0.17
     Norton
    0.15
    jet
    0.15
     Han
    0.15
     Hold
    0.14
     Tek
    0.14
     Wa
    0.14
    èijī
    0.14
     Scotia
    0.14
    holm
    0.14
    Activations Density 0.010%

    No Known Activations