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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-32K
    6. 2812
    Prev
    Next
    INDEX
    Explanations

    references to classical literature and historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otty
    -0.16
    arten
    -0.16
    umin
    -0.15
    ãĥ¼ãĥĨ
    -0.15
    osten
    -0.15
    Persona
    -0.14
    BOSE
    -0.14
    Bonjour
    -0.14
     Kosten
    -0.14
    rana
    -0.14
    POSITIVE LOGITS
    Ñĥ
    0.16
    ium
    0.15
    .cgi
    0.15
    yc
    0.14
    alyze
    0.14
    uant
    0.14
    stitute
    0.14
    ynes
    0.14
    491
    0.13
     LLP
    0.13
    Activations Density 0.059%

    No Known Activations