© 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. 6-LLAMASCOPE-RES-32K
    6. 11751
    Prev
    Next
    INDEX
    Explanations

    the word "right" and its variations in position and context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andest
    -0.16
    é¼
    -0.15
    ruta
    -0.15
    į°
    -0.15
    _ASSUME
    -0.15
    hra
    -0.15
    rlen
    -0.14
    ranÃŃ
    -0.14
    ataire
    -0.14
    寧
    -0.14
    POSITIVE LOGITS
    zeitig
    0.21
    -ÑĤаки
    0.20
    ornado
    0.15
    t
    0.15
    876
    0.15
    142
    0.15
    eo
    0.14
     Documentation
    0.14
    leigh
    0.14
    arent
    0.14
    Activations Density 0.038%

    No Known Activations