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. 28-LLAMASCOPE-RES-32K
    6. 23094
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to programming and mathematical equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Westbrook
    -0.13
     IDirect
    -0.13
    DMI
    -0.13
    anke
    -0.13
    ioneer
    -0.13
    empt
    -0.13
    unlink
    -0.13
     @}
    -0.12
     predecess
    -0.12
    PointerException
    -0.12
    POSITIVE LOGITS
    {-#
    0.13
     à¤ķरà¤ķ
    0.12
    oming
    0.12
    sten
    0.12
    .googlecode
    0.12
    .Guid
    0.12
    tones
    0.12
    fol
    0.12
    iferay
    0.11
    leared
    0.11
    Activations Density 0.146%

    No Known Activations