© 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. 6264
    Prev
    Next
    INDEX
    Explanations

    words associated with growth, enhancement, and improvement

    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
    ÃĹ↵↵
    -0.17
    .Unity
    -0.15
    ocene
    -0.15
    æı
    -0.15
    zig
    -0.14
    á»ĥ
    -0.14
    _INFINITY
    -0.14
    NESS
    -0.14
    arness
    -0.14
    resizing
    -0.14
    POSITIVE LOGITS
    aware
    0.17
     awareness
    0.16
    fir
    0.15
    /im
    0.15
    lein
    0.14
     Gerald
    0.14
     Throw
    0.14
    achen
    0.14
    angen
    0.14
    ä¸Ģä¸ĭ
    0.14
    Activations Density 0.108%

    No Known Activations