© 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. 10-LLAMASCOPE-RES-32K
    11. 3559
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding societal norms and injustices related to gender and race

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illow
    -0.16
    boxed
    -0.15
    urve
    -0.14
    ÏĢη
    -0.14
    Interval
    -0.14
    ILER
    -0.14
    OTTOM
    -0.14
    .bootstrap
    -0.13
     Interval
    -0.13
    olie
    -0.13
    POSITIVE LOGITS
    baum
    0.17
    aldi
    0.16
    ska
    0.16
     PRI
    0.15
     Celt
    0.15
     attr
    0.15
    angan
    0.14
    éĢ
    0.14
    Ïģεια
    0.14
     own
    0.13
    Activations Density 0.253%

    No Known Activations