Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 20886
    Prev
    Next
    INDEX
    Explanations

    references to recording, retrieving, and handling data or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unker
    -0.17
     gag
    -0.15
    æļ
    -0.15
    ropp
    -0.14
    оÑĢи
    -0.14
    ayo
    -0.14
    adera
    -0.13
    รà¸ĩ
    -0.13
    \Type
    -0.13
    .raise
    -0.13
    POSITIVE LOGITS
     later
    0.27
    later
    0.21
     whenever
    0.19
    Later
    0.19
     Later
    0.19
     retrieval
    0.19
     anytime
    0.17
     again
    0.17
     retrieve
    0.17
     später
    0.17
    Activations Density 0.178%

    No Known Activations