© 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. 15-LLAMASCOPE-RES-32K
    11. 28992
    Prev
    Next
    INDEX
    Explanations

    phrases related to catching up or regaining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imli
    -0.19
    chner
    -0.17
    öl
    -0.16
    herits
    -0.15
    º«
    -0.15
    stk
    -0.15
    872
    -0.15
    аÑĤо
    -0.15
    ÂŃi
    -0.15
    åħĪçĶŁ
    -0.14
    POSITIVE LOGITS
     catching
    0.29
     caught
    0.28
     Catch
    0.28
     catches
    0.28
     catch
    0.28
    Catch
    0.26
    caught
    0.25
    catch
    0.24
    -catching
    0.21
     Caught
    0.19
    Activations Density 0.034%

    No Known Activations