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. 1-LLAMASCOPE-RES-32K
    6. 2395
    Prev
    Next
    INDEX
    Explanations

    terms related to financial agreements and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /vnd
    -0.18
    _DSP
    -0.16
    -valu
    -0.15
    ahat
    -0.15
    ±
    -0.15
    олÑı
    -0.15
    .sap
    -0.15
    ÄĽst
    -0.15
    dük
    -0.14
    vation
    -0.14
    POSITIVE LOGITS
    kits
    0.15
    forge
    0.15
    .Void
    0.15
    tram
    0.14
     ring
    0.14
    egl
    0.14
    checker
    0.13
    ávÄĽ
    0.13
    pci
    0.13
    OUS
    0.13
    Activations Density 0.326%

    No Known Activations