© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8207
    Prev
    Next
    INDEX
    Explanations

    themes related to social injustice and historical inequities

    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
    aug
    -0.16
    aira
    -0.14
    iyah
    -0.14
     Hak
    -0.14
    kea
    -0.14
    uckle
    -0.13
    linger
    -0.13
    리ìĸ´
    -0.13
    azor
    -0.13
    ancia
    -0.13
    POSITIVE LOGITS
    à¤¾à¤Ł
    0.15
     Burr
    0.14
     lesbi
    0.13
    à¹Īำ
    0.13
     Stark
    0.13
    loe
    0.13
    .Selenium
    0.13
     podrob
    0.12
     Slots
    0.12
     Kasich
    0.12
    Activations Density 1.009%

    No Known Activations