© 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. 26-LLAMASCOPE-RES-32K
    11. 28608
    Prev
    Next
    INDEX
    Explanations

    references to businesses, ownership, and professional roles within the context of the text

    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
    edback
    -0.14
    rych
    -0.13
    Ñĭвал
    -0.13
    @Inject
    -0.13
    sız
    -0.13
    duÄŁ
    -0.13
    rive
    -0.13
    ItemAt
    -0.12
    <const
    -0.12
    óż
    -0.12
    POSITIVE LOGITS
     themselves
    1.44
     himself
    1.38
     herself
    1.35
     itself
    1.34
     Himself
    1.14
     yourself
    1.12
     ourselves
    1.11
     oneself
    1.02
     yourselves
    1.00
     Yourself
    0.98
    Activations Density 1.576%

    No Known Activations