© 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. 26-LLAMASCOPE-RES-32K
    11. 28204
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and provinces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oup
    -0.16
    ziej
    -0.15
    oger
    -0.13
     newY
    -0.13
    Ĥæķ°
    -0.13
     Nations
    -0.13
    sonian
    -0.13
    Âłmi
    -0.13
     ÙħÛĮÙĦادÛĮ
    -0.13
     newPosition
    -0.13
    POSITIVE LOGITS
     province
    0.39
     Province
    0.34
     region
    0.34
    çľģ
    0.29
     Governor
    0.26
    province
    0.26
    -region
    0.26
    region
    0.25
     Region
    0.24
    Province
    0.23
    Activations Density 0.068%

    No Known Activations