© 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. 31-LLAMASCOPE-RES-32K
    11. 31385
    Prev
    Next
    INDEX
    Explanations

    prominent figures and their roles or achievements in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     notifier
    -0.13
    *=*=
    -0.12
     requires
    -0.12
    Requires
    -0.12
    requires
    -0.12
     bloodstream
    -0.11
    -prepend
    -0.11
     acum
    -0.11
    ilated
    -0.11
    лена
    -0.11
    POSITIVE LOGITS
     discusses
    0.39
     discuss
    0.38
     talks
    0.37
     chats
    0.36
     shares
    0.32
     Discuss
    0.31
     previews
    0.31
     talk
    0.29
     discussing
    0.29
     share
    0.28
    Activations Density 0.135%

    No Known Activations