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. 709
    Prev
    Next
    INDEX
    Explanations

    references to scientific articles or studies

    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
     barr
    -0.16
    erland
    -0.15
    chalk
    -0.15
    aub
    -0.15
    æĬŀ
    -0.14
    oq
    -0.14
    گاب
    -0.14
    मत
    -0.14
     openings
    -0.14
    yte
    -0.14
    POSITIVE LOGITS
     kazan
    0.17
     confidence
    0.15
     Confidence
    0.14
     Kemal
    0.14
    za
    0.14
    etter
    0.14
     Earth
    0.14
    ilers
    0.14
    ène
    0.14
     cov
    0.13
    Activations Density 0.000%

    No Known Activations