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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 15819
    Prev
    Next
    INDEX
    Explanations

    phrases associated with organization and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auc
    -0.15
    cts
    -0.15
    ัà¸ķà¸ĸ
    -0.15
    ei
    -0.15
    थ
    -0.14
    ifter
    -0.14
     Nem
    -0.14
    zelf
    -0.14
    kok
    -0.14
    ?key
    -0.14
    POSITIVE LOGITS
    ÃŃte
    0.14
     Leh
    0.14
    ypes
    0.14
    .LoggerFactory
    0.14
    ills
    0.14
    ouz
    0.14
     singled
    0.14
    orney
    0.14
    ouve
    0.13
    344
    0.13
    Activations Density 0.002%

    No Known Activations