© 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. 24-LLAMASCOPE-RES-32K
    6. 5125
    Prev
    Next
    INDEX
    Explanations

    references to specific wildlife species found in the Amazon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cape
    -0.16
    è³
    -0.15
    /includes
    -0.15
     Cape
    -0.14
     suburbs
    -0.14
    esium
    -0.14
    ä½Ļ
    -0.14
    ãĥ¼ãĥĢ
    -0.14
     winters
    -0.14
    agr
    -0.14
    POSITIVE LOGITS
     Amazon
    0.46
    Amazon
    0.43
     amazon
    0.39
    amazon
    0.36
    .amazon
    0.33
    mazon
    0.32
     rain
    0.24
     Rain
    0.24
     Guy
    0.23
    Guy
    0.22
    Activations Density 0.059%

    No Known Activations