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. 7-LLAMASCOPE-RES-32K
    6. 13635
    Prev
    Next
    INDEX
    Explanations

    ingredients and items related to brewing or cooking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    οÏħλ
    -0.15
    actic
    -0.15
    apon
    -0.15
    RTL
    -0.14
     ÙĤدر
    -0.14
    itech
    -0.14
    γÏģαμμα
    -0.14
    éĺħ读次æķ°
    -0.14
     UObject
    -0.14
    ctica
    -0.14
    POSITIVE LOGITS
    auto
    0.14
    ãĥĥãĤ·ãĥ¥
    0.14
    bek
    0.14
    sd
    0.14
    oven
    0.13
    levator
    0.13
    dev
    0.13
    .echo
    0.13
    aper
    0.13
    aption
    0.13
    Activations Density 0.025%

    No Known Activations