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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16514
    Prev
    Next
    INDEX
    Explanations

    references to significant events or gatherings, particularly related to LGBTQ+ pride and political demonstrations

    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
    592
    -0.17
    ัà¸ķà¸ĸ
    -0.15
    ุล
    -0.15
     ?>"/>↵
    -0.14
     нам
    -0.14
     æ¹
    -0.14
    nda
    -0.14
    ceae
    -0.14
    olec
    -0.14
    mtree
    -0.14
    POSITIVE LOGITS
    zet
    0.14
    _CSV
    0.14
     Atmos
    0.14
    åĢį
    0.14
     hoped
    0.13
     Cleveland
    0.13
    isco
    0.13
     nghe
    0.13
    aur
    0.12
    756
    0.12
    Activations Density 0.252%

    No Known Activations