© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 11-LLAMASCOPE-RES-32K
    11. 26684
    Prev
    Next
    INDEX
    Explanations

    phrases related to clarity, organization, and effective communication in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     strokeLine
    -0.14
    chie
    -0.14
     aspects
    -0.14
    abor
    -0.14
    имÑĥ
    -0.14
    yer
    -0.13
     ones
    -0.13
    ัà¹Ī
    -0.13
    _framework
    -0.13
    edeki
    -0.13
    POSITIVE LOGITS
     sorts
    0.16
    orraine
    0.14
     MERCHANTABILITY
    0.14
     possibile
    0.14
    erdale
    0.14
     Gross
    0.14
    ertest
    0.13
     Conrad
    0.13
    REDIT
    0.13
    uiten
    0.13
    Activations Density 0.911%

    No Known Activations