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. 28-LLAMASCOPE-RES-32K
    6. 418
    Prev
    Next
    INDEX
    Explanations

    expressions related to "half" or partial quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    575
    -0.17
    絡
    -0.15
    all
    -0.15
    648
    -0.15
    able
    -0.14
    >window
    -0.14
    anical
    -0.14
    lav
    -0.14
    geois
    -0.14
    usu
    -0.14
    POSITIVE LOGITS
     dozen
    0.30
    /full
    0.26
    ords
    0.24
    moon
    0.24
    heart
    0.23
     Moon
    0.20
    -hearted
    0.20
     baked
    0.20
    way
    0.19
    aker
    0.19
    Activations Density 0.033%

    No Known Activations