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. 20-LLAMASCOPE-RES-32K
    6. 23833
    Prev
    Next
    INDEX
    Explanations

    phrases that simplify or clarify complex concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ium
    -0.15
    alus
    -0.15
    obot
    -0.14
    oin
    -0.14
    le
    -0.14
    öl
    -0.14
    eprom
    -0.14
    alon
    -0.13
    arez
    -0.13
     Kosten
    -0.13
    POSITIVE LOGITS
     basically
    0.45
     essentially
    0.42
     Basically
    0.40
    Basically
    0.38
     simply
    0.37
     Essentially
    0.36
     Simply
    0.34
    Simply
    0.33
     simple
    0.32
    bas
    0.31
    Activations Density 0.229%

    No Known Activations