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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 2-LLAMASCOPE-RES-32K
    11. 30562
    Prev
    Next
    INDEX
    Explanations

    instances of the word "navigate" and its variations, indicating a focus on guidance and direction within contexts of complexity or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sst
    -0.15
    νÏĦ
    -0.15
    ç¾½
    -0.15
    ément
    -0.15
    ansion
    -0.14
    edom
    -0.14
    én
    -0.14
    ÏĦÏİ
    -0.14
    avax
    -0.14
    iveness
    -0.13
    POSITIVE LOGITS
    LETTE
    0.16
    888
    0.16
    agh
    0.15
    113
    0.14
    ette
    0.14
    her
    0.14
     virgin
    0.14
    /navigation
    0.14
    usu
    0.14
    esk
    0.13
    Activations Density 0.031%

    No Known Activations