© 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. 23021
    Prev
    Next
    INDEX
    Explanations

    names of individuals and specific locations or events related to sports

    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
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.20
     Bylo
    -0.19
     att
    -0.18
    pedia
    -0.17
     Spy
    -0.17
    ville
    -0.16
     بÛĮر
    -0.16
    ejména
    -0.15
    spy
    -0.15
     blur
    -0.15
    POSITIVE LOGITS
    Portály
    0.19
     pod
    0.18
     porr
    0.17
    oba
    0.16
    oby
    0.16
     dedi
    0.16
    oute
    0.16
     VÅ¡ech
    0.15
     Poh
    0.15
    icky
    0.15
    Activations Density 0.054%

    No Known Activations