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. 11-LLAMASCOPE-RES-32K
    6. 998
    Prev
    Next
    INDEX
    Explanations

    references to surveillance and security systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ehler
    -0.15
    eny
    -0.15
    ugu
    -0.14
     CF
    -0.14
    elivery
    -0.13
    sik
    -0.13
     Takes
    -0.13
     {?>↵
    -0.13
    _TRAN
    -0.13
     dot
    -0.13
    POSITIVE LOGITS
    obra
    0.15
    á»ĭ
    0.15
    itia
    0.14
    achat
    0.14
     intens
    0.14
    EventManager
    0.14
     surv
    0.14
    .extent
    0.14
    amera
    0.13
    igr
    0.13
    Activations Density 0.031%

    No Known Activations