© 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. 9-LLAMASCOPE-RES-32K
    11. 26816
    Prev
    Next
    INDEX
    Explanations

    terms associated with government restrictions and policies, particularly related to immigration and watch lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    วล
    -0.15
    ÅŁÄ±
    -0.15
    eters
    -0.14
    .gradient
    -0.14
    IGNAL
    -0.14
    iets
    -0.14
    ubbo
    -0.14
    lers
    -0.14
    enary
    -0.14
     Fus
    -0.14
    POSITIVE LOGITS
    QP
    0.17
     Ard
    0.17
    lid
    0.15
    osta
    0.15
    ardy
    0.14
     villain
    0.14
    jing
    0.13
     quad
    0.13
     blonde
    0.13
    asz
    0.13
    Activations Density 0.004%

    No Known Activations