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. 1-LLAMASCOPE-RES-32K
    6. 23228
    Prev
    Next
    INDEX
    Explanations

    references to permissions and HTTP request handling in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leh
    -0.15
    etic
    -0.15
     ant
    -0.14
    corn
    -0.14
    zie
    -0.14
     regard
    -0.14
    quil
    -0.13
    erman
    -0.13
    art
    -0.13
    chen
    -0.13
    POSITIVE LOGITS
    ศาสà¸ķร
    0.17
    yre
    0.17
    uraa
    0.15
    uge
    0.15
    uvo
    0.14
    缼
    0.14
    ehr
    0.14
    صة
    0.14
     Hammond
    0.14
    ukan
    0.14
    Activations Density 0.009%

    No Known Activations