© 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. 30-LLAMASCOPE-RES-32K
    11. 18820
    Prev
    Next
    INDEX
    Explanations

    references to Google services and their transitions or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gfx
    -0.19
    ouz
    -0.17
     XB
    -0.17
    obao
    -0.15
    Gui
    -0.15
    XB
    -0.15
    /GPL
    -0.15
    ãĤ¹ãĥĨãĤ£
    -0.15
    ØŃداث
    -0.14
    Enumerator
    -0.14
    POSITIVE LOGITS
     Assistant
    0.25
     RCS
    0.24
     Dup
    0.21
     assistant
    0.19
     AR
    0.19
     Lens
    0.19
    Assistant
    0.18
    acio
    0.18
     Material
    0.17
     Duo
    0.17
    Activations Density 0.028%

    No Known Activations