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. 8-LLAMASCOPE-RES-32K
    6. 6533
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical equations and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    577
    -0.19
    isy
    -0.17
    ply
    -0.16
    اÛĮر
    -0.15
    antz
    -0.15
    à¥įयत
    -0.15
    å¹¹
    -0.14
    anos
    -0.14
    ardon
    -0.14
    ìĹĶ
    -0.14
    POSITIVE LOGITS
    ardi
    0.16
    AndView
    0.15
    vang
    0.14
     depth
    0.14
    ayan
    0.14
     Depth
    0.14
     á»§y
    0.14
    ¦æĥħ
    0.14
    eld
    0.13
    abwe
    0.13
    Activations Density 0.062%

    No Known Activations