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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 17594
    Prev
    Next
    INDEX
    Explanations

    references to racial and socio-economic disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avoid
    -0.19
    éģ¿
    -0.17
    Avoid
    -0.16
    olon
    -0.16
     Avoid
    -0.16
    avoid
    -0.15
    ازÙĩ
    -0.15
    ould
    -0.15
     prevent
    -0.14
    OLON
    -0.14
    POSITIVE LOGITS
     black
    0.51
     Black
    0.44
    black
    0.43
    Black
    0.41
    é»ij
    0.40
     BLACK
    0.39
     African
    0.37
    é»Ĵ
    0.37
    -black
    0.37
    BLACK
    0.34
    Activations Density 0.145%

    No Known Activations