Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 23298
    Prev
    Next
    INDEX
    Explanations

    mentions of ethnic groups and cultural identities

    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
    indr
    -0.17
    leich
    -0.16
     Loren
    -0.15
    yna
    -0.15
    g
    -0.14
    ynam
    -0.14
    ers
    -0.14
    ifer
    -0.14
    yn
    -0.14
    patches
    -0.13
    POSITIVE LOGITS
    -Muslim
    0.15
     nackt
    0.15
    bau
    0.14
    illy
    0.14
    BuilderFactory
    0.14
    à¹Ģà¸ķà¸Ńร
    0.14
    _Float
    0.14
    latlong
    0.13
    onders
    0.13
    abor
    0.13
    Activations Density 0.272%

    No Known Activations