© 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. 26-LLAMASCOPE-RES-32K
    11. 29919
    Prev
    Next
    INDEX
    Explanations

    concepts related to support and mentorship dynamics

    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
    ạch
    -0.14
    rupa
    -0.13
    >[]
    -0.13
    loquent
    -0.12
    aeda
    -0.12
    ENTE
    -0.12
     ìŀIJìĭłìĿĺ
    -0.11
    ovalo
    -0.11
    loys
    -0.11
    ãģĮãģĬ
    -0.11
    POSITIVE LOGITS
     them
    1.34
    them
    1.06
     ihnen
    0.94
     they
    0.84
     ниÑħ
    0.83
     ellos
    0.82
     mereka
    0.80
     Them
    0.77
     THEM
    0.75
     ними
    0.74
    Activations Density 1.438%

    No Known Activations