© 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. 7-LLAMASCOPE-RES-32K
    11. 24212
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the word "an" and references to secrets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eldo
    -0.14
    umatic
    -0.14
    ylon
    -0.13
    олÑĮно
    -0.13
    eof
    -0.13
     Grocery
    -0.13
    лÑĥ
    -0.13
    elig
    -0.13
    services
    -0.13
     Dub
    -0.13
    POSITIVE LOGITS
    ÑĢеп
    0.17
    ertest
    0.17
     McGill
    0.16
    antt
    0.14
    ิà¸į
    0.14
     celebr
    0.13
    .ImageAlign
    0.13
    NZ
    0.13
    å·±
    0.13
    ingle
    0.13
    Activations Density 0.021%

    No Known Activations