© 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. 4-LLAMASCOPE-RES-32K
    11. 23799
    Prev
    Next
    INDEX
    Explanations

    repeated patterns and variations of the word "for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nameof
    -0.15
    urger
    -0.15
    currentColor
    -0.15
    cher
    -0.15
    µľ
    -0.14
    Ïĥια
    -0.14
    iswa
    -0.14
    allet
    -0.14
     Tropical
    -0.14
     Demir
    -0.14
    POSITIVE LOGITS
    gers
    0.17
     Coleman
    0.15
    geç
    0.13
    jumbotron
    0.13
     Dro
    0.13
    è®
    0.13
    venues
    0.13
    anoia
    0.13
    ίκ
    0.13
    ÙħÙĪÙĦ
    0.13
    Activations Density 0.237%

    No Known Activations