© 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. 9594
    Prev
    Next
    INDEX
    Explanations

    patterns of formal language and legal terminology

    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
     diversos
    -0.22
    “He
    -0.21
    "He
    -0.20
     каждого
    -0.19
     byli
    -0.19
    ÑĥÑĪка
    -0.18
     boys
    -0.18
     каждÑĭй
    -0.17
     varios
    -0.17
    наÑı
    -0.16
    POSITIVE LOGITS
    adas
    0.46
    áticas
    0.45
     elles
    0.45
     ellas
    0.44
    nicas
    0.42
    ativas
    0.39
    ÃŃsticas
    0.38
    adoras
    0.38
    uestas
    0.37
    las
    0.36
    Activations Density 0.130%

    No Known Activations