© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    articles and determiners like "a" and "an" in various contexts

    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
     bankrupt
    -0.15
    UNK
    -0.15
     Guill
    -0.14
     Ort
    -0.14
     mile
    -0.14
     Sur
    -0.14
    uibModal
    -0.14
    acey
    -0.14
     miles
    -0.14
     late
    -0.14
    POSITIVE LOGITS
    кÑĥÑģ
    0.17
    ë§¹
    0.15
    _SWAP
    0.15
    seite
    0.15
    дÑĢеÑģ
    0.14
    vvm
    0.14
    theon
    0.14
    ledon
    0.14
    assa
    0.14
    figcaption
    0.14
    Activations Density 0.258%

    No Known Activations