© 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. 18-LLAMASCOPE-RES-32K
    11. 25901
    Prev
    Next
    INDEX
    Explanations

    mentions of school safety measures and related policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     undergrad
    -0.16
     undergraduate
    -0.15
    Women
    -0.15
    女æĢ§
    -0.15
     extradition
    -0.14
    :Object
    -0.14
    ÑģÑĤе
    -0.14
     Women
    -0.13
     apprent
    -0.13
    ÙģÙĩ
    -0.13
    POSITIVE LOGITS
     school
    0.46
     schools
    0.42
    .school
    0.38
    school
    0.36
     Schools
    0.35
     School
    0.35
    School
    0.35
    schools
    0.33
    åŃ¦æł¡
    0.33
     SCHOOL
    0.32
    Activations Density 1.239%

    No Known Activations