© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 24839
    Prev
    Next
    INDEX
    Explanations

    references to authors and their works, especially books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     une
    -0.16
     Clip
    -0.15
    phan
    -0.14
    partment
    -0.14
     Biography
    -0.14
    Shared
    -0.13
     Zu
    -0.13
     isolated
    -0.12
     technicians
    -0.12
     directors
    -0.12
    POSITIVE LOGITS
     book
    0.52
     books
    0.40
    book
    0.39
    -book
    0.38
     кни
    0.36
     libro
    0.35
     livro
    0.34
    _book
    0.33
    书
    0.33
    (book
    0.32
    Activations Density 0.226%

    No Known Activations