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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 7425
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their professional roles or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aken
    -0.15
    obe
    -0.15
    alted
    -0.14
    Introduction
    -0.13
     composition
    -0.13
    ehler
    -0.13
     competitive
    -0.13
     U
    -0.13
    compose
    -0.13
    cha
    -0.13
    POSITIVE LOGITS
     joined
    0.33
    joined
    0.31
     Joined
    0.31
    Joined
    0.28
     Join
    0.25
     joining
    0.25
     prior
    0.23
    Join
    0.22
     join
    0.22
     Prior
    0.21
    Activations Density 0.057%

    No Known Activations