© 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. 25-LLAMASCOPE-RES-32K
    11. 17885
    Prev
    Next
    INDEX
    Explanations

    discussions around gender roles and the experiences of women

    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
    adder
    -0.15
    engin
    -0.15
    oze
    -0.14
    ibold
    -0.14
    issen
    -0.14
     Rac
    -0.14
    ola
    -0.13
    cele
    -0.13
    rac
    -0.13
    æĮĤ
    -0.13
    POSITIVE LOGITS
     roles
    0.25
     homem
    0.24
     Roles
    0.22
    roles
    0.21
    Roles
    0.21
     domestic
    0.20
     passive
    0.18
    .roles
    0.18
     weaker
    0.18
     cooking
    0.18
    Activations Density 0.185%

    No Known Activations