© 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. 8-LLAMASCOPE-RES-32K
    11. 1408
    Prev
    Next
    INDEX
    Explanations

    phrases and structures related to examples and conditional scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orrent
    -0.17
    upo
    -0.15
     Pearce
    -0.15
     Snow
    -0.15
    DY
    -0.14
     col
    -0.14
     Suc
    -0.14
    ê¶Į
    -0.14
     Tess
    -0.14
     ph
    -0.13
    POSITIVE LOGITS
    atables
    0.16
    toolbox
    0.15
    heit
    0.15
    èģ
    0.15
    adders
    0.14
    setLayout
    0.14
     Listening
    0.14
    amber
    0.14
    asion
    0.14
    ysqli
    0.14
    Activations Density 0.208%

    No Known Activations