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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 1932
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematics and physics, particularly those involving constants and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aces
    -0.15
     ÙģÙĪ
    -0.14
    omin
    -0.14
    dol
    -0.14
     Mines
    -0.14
    oq
    -0.14
    enan
    -0.13
     motions
    -0.13
    uel
    -0.13
    aminer
    -0.13
    POSITIVE LOGITS
     parameters
    0.47
     Parameters
    0.40
     constants
    0.39
    parameters
    0.36
    Parameters
    0.34
     parameter
    0.34
     PARAMETERS
    0.33
    constants
    0.31
     Constants
    0.31
    åıĤæķ°
    0.29
    Activations Density 0.363%

    No Known Activations