© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 25254
    Prev
    Next
    INDEX
    Explanations

    patterns related to regular expressions

    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
    /archive
    -0.16
    ç¶ĵ
    -0.15
    жи
    -0.14
    orf
    -0.14
    виÑĩ
    -0.14
    æ®Ĭ
    -0.14
    ÏĦιν
    -0.13
    à¤Ĥà¤ľà¤¨
    -0.13
    OOT
    -0.13
    ë©´
    -0.13
    POSITIVE LOGITS
    ppy
    0.16
    iesen
    0.14
    attern
    0.14
    ิà¸Ļà¸Ĺ
    0.14
    tre
    0.14
    ix
    0.14
    lassen
    0.14
    isher
    0.13
    clud
    0.13
    daq
    0.13
    Activations Density 0.020%

    No Known Activations