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. 21-LLAMASCOPE-RES-32K
    6. 9853
    Prev
    Next
    INDEX
    Explanations

    legal references and citations related to court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neck
    -0.15
    alfa
    -0.14
    ilk
    -0.14
    lat
    -0.14
    TestFixture
    -0.14
     rope
    -0.13
     topl
    -0.13
     Wa
    -0.13
     Rope
    -0.13
    endale
    -0.13
    POSITIVE LOGITS
    ìĦľ
    0.17
    ');?>"
    0.16
    sup
    0.16
     supra
    0.16
    nard
    0.14
    esktop
    0.14
    ILON
    0.14
    ertime
    0.14
    .dest
    0.14
    инов
    0.14
    Activations Density 0.032%

    No Known Activations