© 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. 4-LLAMASCOPE-RES-32K
    11. 14761
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with white supremacy and racist ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enson
    -0.18
    olie
    -0.16
     stro
    -0.15
    jang
    -0.15
    rupa
    -0.15
     Dash
    -0.15
    pleted
    -0.15
     Verm
    -0.14
     rect
    -0.14
    inent
    -0.14
    POSITIVE LOGITS
    imizer
    0.15
     Sadd
    0.14
    praak
    0.14
    ì
    0.14
    Sortable
    0.14
    vir
    0.14
    ablish
    0.14
    ?option
    0.13
    edom
    0.13
    ître
    0.13
    Activations Density 0.048%

    No Known Activations