© 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. 28-LLAMASCOPE-RES-32K
    11. 27723
    Prev
    Next
    INDEX
    Explanations

    significant people and events related to history or notable occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    аза
    -0.12
    UGH
    -0.12
    IELD
    -0.12
    ÑİÑĢ
    -0.12
     papers
    -0.12
    ?type
    -0.11
     lucrative
    -0.11
    лагод
    -0.11
    astro
    -0.11
    ?page
    -0.11
    POSITIVE LOGITS
     Photo
    0.58
     Credit
    0.55
    Photo
    0.55
    Credit
    0.53
     Image
    0.51
     photo
    0.51
     credit
    0.49
    Image
    0.49
    credit
    0.46
    .Photo
    0.43
    Activations Density 0.528%

    No Known Activations