© 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. 23-LLAMASCOPE-RES-32K
    11. 12269
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "read more," indicating additional content or references to further reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤŃãĥ£
    -0.17
    елÑİ
    -0.17
     Middleton
    -0.16
    ottie
    -0.15
    oon
    -0.15
    .INSTANCE
    -0.15
     Heg
    -0.14
     zav
    -0.14
    NIL
    -0.14
     Greenwood
    -0.14
    POSITIVE LOGITS
    alendar
    0.17
    edir
    0.15
    _FATAL
    0.15
    å¥ı
    0.14
    Forge
    0.14
    fos
    0.14
    893
    0.13
    /buttons
    0.13
    çº
    0.13
    .documentation
    0.13
    Activations Density 0.003%

    No Known Activations