© 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. 1904
    Prev
    Next
    INDEX
    Explanations

    references to "night" and related terms

    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
    hort
    -0.17
    thouse
    -0.16
    ÏĮÏģ
    -0.14
    xae
    -0.14
    -animate
    -0.14
    åħIJ
    -0.14
     Collider
    -0.14
    дап
    -0.13
    apo
    -0.13
    hip
    -0.13
    POSITIVE LOGITS
    clubs
    0.37
    shade
    0.36
    ime
    0.33
    crawler
    0.33
    shift
    0.32
    fall
    0.32
    -time
    0.32
    mar
    0.31
    mares
    0.31
    time
    0.31
    Activations Density 0.016%

    No Known Activations