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

    Neuronpedia

    APICircuit 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. 25-LLAMASCOPE-RES-32K
    6. 278
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to conditions, requirements, and modifications in agreements or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĥĸ
    -0.15
    È
    -0.14
    -urlencoded
    -0.14
    .Pages
    -0.13
    nex
    -0.12
    bee
    -0.12
    olon
    -0.12
    oker
    -0.12
    ndon
    -0.12
    .communication
    -0.12
    POSITIVE LOGITS
     above
    1.34
    above
    1.15
     Above
    1.07
    Above
    1.05
     ABOVE
    0.98
     вÑĭÑĪе
    0.83
    _above
    0.82
     aforementioned
    0.80
    以ä¸Ĭ
    0.79
    bove
    0.76
    Activations Density 0.581%

    No Known Activations