© 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. 20-LLAMASCOPE-RES-32K
    11. 31472
    Prev
    Next
    INDEX
    Explanations

    references to communication or outreach activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rite
    -0.17
    erte
    -0.15
    annah
    -0.15
    ihn
    -0.14
    rial
    -0.14
    iente
    -0.14
    rowse
    -0.13
    rahim
    -0.13
    zw
    -0.13
    plier
    -0.13
    POSITIVE LOGITS
     about
    0.24
    about
    0.20
     directly
    0.19
    _about
    0.19
     regarding
    0.19
    åħ³äºİ
    0.18
     tentang
    0.16
     concerning
    0.16
    -about
    0.16
     vá»ģ
    0.16
    Activations Density 0.097%

    No Known Activations