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. 20827
    Prev
    Next
    INDEX
    Explanations

    references to "ground" or "groundbreaking" concepts or occurrences

    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
    oot
    -0.15
    INO
    -0.14
    ather
    -0.14
    uyen
    -0.14
    æľĭ
    -0.14
    otes
    -0.13
    -dot
    -0.13
    zes
    -0.13
    .fs
    -0.13
    otto
    -0.13
    POSITIVE LOGITS
    hog
    0.22
    -ground
    0.19
    edly
    0.18
    -ÑĤаки
    0.18
    608
    0.17
     ground
    0.17
    eri
    0.17
    sw
    0.17
    arella
    0.16
    稿
    0.16
    Activations Density 0.040%

    No Known Activations