© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15939
    Prev
    Next
    INDEX
    Explanations

    phrases related to risks and outcomes in various contexts

    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
    iana
    -0.15
    elas
    -0.14
    ador
    -0.14
    اساÙĨ
    -0.14
    OMIC
    -0.13
    олÑİ
    -0.13
    ior
    -0.13
    UnderTest
    -0.13
    ádu
    -0.12
     deserving
    -0.12
    POSITIVE LOGITS
     successful
    1.15
    successful
    1.00
     Successful
    1.00
    æĪIJåĬŁ
    0.96
    Successful
    0.92
     successfully
    0.92
     success
    0.86
     succes
    0.85
    successfully
    0.81
     ÑĥÑģпеÑĪ
    0.80
    Activations Density 0.449%

    No Known Activations