© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 12518
    Prev
    Next
    INDEX
    Explanations

    italicized descriptive phrases related to actions and conditions of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gos
    -0.17
    mán
    -0.16
    uchs
    -0.15
    ibold
    -0.14
    ouve
    -0.14
    $MESS
    -0.14
    ighth
    -0.14
     --
    -0.14
    uml
    -0.14
    GLISH
    -0.14
    POSITIVE LOGITS
     incor
    0.15
    éĻ¶
    0.14
    aid
    0.14
     %[
    0.14
    Ïģί
    0.13
    cms
    0.13
    fo
    0.13
     Unt
    0.13
    unt
    0.13
    sc
    0.13
    Activations Density 0.371%

    No Known Activations