© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 6042
    Prev
    Next
    INDEX
    Explanations

    geographical and ecological relationships among species and their habitats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geois
    -0.16
    cci
    -0.15
    icode
    -0.15
    izza
    -0.14
     phá»ij
    -0.14
    atown
    -0.14
    Clr
    -0.13
     جاÙħع
    -0.13
    pec
    -0.13
    _timezone
    -0.13
    POSITIVE LOGITS
     central
    0.32
     western
    0.24
     portions
    0.24
    central
    0.23
     Central
    0.23
     Western
    0.23
     parts
    0.23
     interior
    0.23
     extreme
    0.22
     Northwestern
    0.22
    Activations Density 0.223%

    No Known Activations