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. 3-LLAMASCOPE-RES-32K
    6. 181
    Prev
    Next
    INDEX
    Explanations

    technical terms and code structures related to programming templates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gust
    -0.16
     ev
    -0.15
    éĦ
    -0.15
     len
    -0.14
    AKE
    -0.14
     innoc
    -0.14
    ushman
    -0.14
    upe
    -0.14
     Nev
    -0.14
    imeters
    -0.14
    POSITIVE LOGITS
    isci
    0.18
    obox
    0.16
     søger
    0.15
    anmar
    0.15
    ink
    0.14
    isc
    0.14
    _java
    0.14
    ستÛĮ
    0.14
    IMA
    0.14
     smr
    0.14
    Activations Density 0.078%

    No Known Activations