© 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. 9-LLAMASCOPE-RES-32K
    11. 23586
    Prev
    Next
    INDEX
    Explanations

    terms related to discrimination and inequality

    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
    ends
    -0.16
    lify
    -0.15
    emo
    -0.15
    تÙĪÙĨ
    -0.14
    /current
    -0.14
     ÙħÛĮÙĦادÛĮ
    -0.14
    spring
    -0.14
    asty
    -0.14
    auto
    -0.14
    oud
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.16
    ulti
    0.16
    bersome
    0.15
    ellen
    0.15
    BootApplication
    0.14
    .ISupportInitialize
    0.14
    iveness
    0.14
    ulerAngles
    0.14
    غاÙĦ
    0.14
    kening
    0.14
    Activations Density 0.023%

    No Known Activations