© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 15885
    Prev
    Next
    INDEX
    Explanations

    elements indicative of academic papers, such as titles, abstracts, and keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enal
    -0.16
    ukkit
    -0.15
    622
    -0.14
     Lane
    -0.14
     Brow
    -0.14
    rouch
    -0.14
    raith
    -0.14
     units
    -0.14
    275
    -0.13
     ie
    -0.13
    POSITIVE LOGITS
    ÑĶм
    0.16
    unread
    0.16
    ict
    0.15
    èĵ
    0.15
    /Peak
    0.15
    _rsa
    0.14
    opsis
    0.14
    ç̬
    0.14
    ãģķãģ¾
    0.14
    izu
    0.14
    Activations Density 0.002%

    No Known Activations