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

    Neuronpedia

    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. 734
    Prev
    Next
    INDEX
    Explanations

    references to the word "old."

    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
    ected
    -0.17
    ะ
    -0.14
    ably
    -0.13
    nett
    -0.13
    lessly
    -0.13
     lifelong
    -0.13
    838
    -0.13
    ACCESS
    -0.13
     кÑĥÑĢ
    -0.13
    reator
    -0.13
    POSITIVE LOGITS
    -fashioned
    0.41
     fashioned
    0.33
    -school
    0.25
    ÅĻich
    0.24
    -old
    0.23
    school
    0.20
    (er
    0.20
    /new
    0.20
    /current
    0.19
    timer
    0.19
    Activations Density 0.056%

    No Known Activations