© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 3-LLAMASCOPE-RES-32K
    6. 16924
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "beyond" or themes related to transcending limits and boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĮĤ
    -0.16
    ayd
    -0.16
    aki
    -0.15
    eed
    -0.15
     XL
    -0.15
     might
    -0.15
    dump
    -0.14
    aan
    -0.14
    chen
    -0.14
    etics
    -0.14
    POSITIVE LOGITS
    inas
    0.15
    é±
    0.15
    kop
    0.15
    verity
    0.15
    ä¹ħä¹ħ
    0.15
    esiz
    0.15
    iteleri
    0.14
    ë²
    0.14
    OwnProperty
    0.14
    mgr
    0.14
    Activations Density 0.010%

    No Known Activations