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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 13-LLAMASCOPE-RES-32K
    6. 19285
    Prev
    Next
    INDEX
    Explanations

    aspects of scientific and genetic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Piece
    -0.17
    immel
    -0.16
    adol
    -0.16
    reator
    -0.16
    ovaly
    -0.16
    asper
    -0.15
    reation
    -0.15
    ritt
    -0.14
    imson
    -0.14
    precated
    -0.14
    POSITIVE LOGITS
     briefly
    0.17
    ysz
    0.15
    lain
    0.15
    GF
    0.14
    кан
    0.13
    OLF
    0.13
    .poi
    0.13
    .lucene
    0.13
    .box
    0.13
    722
    0.13
    Activations Density 0.052%

    No Known Activations