© 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. 9-LLAMASCOPE-RES-32K
    11. 9113
    Prev
    Next
    INDEX
    Explanations

    references to fatalities and injuries in disasters or accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İ
    -0.18
    YST
    -0.16
    rze
    -0.15
    виж
    -0.15
    xl
    -0.15
     Disc
    -0.15
    zie
    -0.15
     Canc
    -0.14
    YSIS
    -0.13
    लब
    -0.13
    POSITIVE LOGITS
    urent
    0.19
    íĥ
    0.15
     commission
    0.14
    achable
    0.14
    orative
    0.14
     اÙĦÙħص
    0.14
     sor
    0.14
    aker
    0.13
    prung
    0.13
    aml
    0.13
    Activations Density 0.032%

    No Known Activations