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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-LLAMASCOPE-RES-32K
    6. 16552
    Prev
    Next
    INDEX
    Explanations

    references to formal processes or regulations involving permissions and approvals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zucker
    -0.16
    orton
    -0.15
    etag
    -0.15
    rif
    -0.14
     cushion
    -0.14
    .SC
    -0.13
     deb
    -0.13
     Dub
    -0.13
     ether
    -0.13
    izard
    -0.13
    POSITIVE LOGITS
     Coverage
    0.19
     coverage
    0.16
    Coverage
    0.16
    essler
    0.15
    éij
    0.15
    auf
    0.15
    ihan
    0.14
    .tencent
    0.14
    ikan
    0.14
    breadcrumbs
    0.14
    Activations Density 0.003%

    No Known Activations