Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 16607
    Prev
    Next
    INDEX
    Explanations

    references to political participation and the interplay between governance and societal issues

    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
    ektor
    -0.15
    heit
    -0.15
    æĹıèĩªæ²»
    -0.14
     commod
    -0.14
     Billion
    -0.13
    á»ĵng
    -0.13
    elsing
    -0.13
     pumping
    -0.13
    ansen
    -0.13
    Ĥæķ°
    -0.12
    POSITIVE LOGITS
     political
    0.88
     politics
    0.87
     Political
    0.74
     Politics
    0.72
    political
    0.70
    æĶ¿æ²»
    0.66
     polÃŃtica
    0.65
     полиÑĤ
    0.61
     politique
    0.60
     polit
    0.60
    Activations Density 0.336%

    No Known Activations