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. 27-LLAMASCOPE-RES-32K
    6. 115
    Prev
    Next
    INDEX
    Explanations

    references to college sports teams, particularly in basketball and football contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    дап
    -0.15
     etc
    -0.14
     FontStyle
    -0.14
     ServiceException
    -0.13
     getSession
    -0.13
    posit
    -0.13
    ETIME
    -0.13
    _AA
    -0.12
    LAN
    -0.12
    boards
    -0.12
    POSITIVE LOGITS
    -bound
    0.19
     native
    0.19
    -born
    0.19
    .edu
    0.18
    -native
    0.18
     forward
    0.17
     University
    0.17
     State
    0.17
     Confidential
    0.16
    çĭ¼
    0.16
    Activations Density 0.069%

    No Known Activations