© 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. 16-LLAMASCOPE-RES-32K
    11. 19171
    Prev
    Next
    INDEX
    Explanations

    items related to product specifications and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     naw
    -0.18
     Nha
    -0.17
    ÑĢава
    -0.16
    ocha
    -0.15
     Illum
    -0.15
    atem
    -0.15
    AND
    -0.14
    ÙĪØ«
    -0.14
    ows
    -0.14
    elda
    -0.14
    POSITIVE LOGITS
    CI
    0.24
     CI
    0.23
     BI
    0.23
     CPI
    0.22
    GI
    0.22
    BI
    0.22
    SI
    0.21
     MI
    0.20
    ci
    0.19
     CIS
    0.19
    Activations Density 0.078%

    No Known Activations