© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 26405
    Prev
    Next
    INDEX
    Explanations

    references to additional information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iors
    -0.17
    ikal
    -0.15
    rico
    -0.15
    aklı
    -0.15
    endcode
    -0.14
    andler
    -0.14
    /umd
    -0.14
    557
    -0.14
    imientos
    -0.13
    QUI
    -0.13
    POSITIVE LOGITS
     details
    0.19
     information
    0.18
     info
    0.16
    quat
    0.15
    information
    0.15
     detail
    0.15
     informatie
    0.15
     informacÃŃ
    0.15
    indre
    0.14
    illon
    0.14
    Activations Density 0.023%

    No Known Activations