© 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. 20-LLAMASCOPE-RES-32K
    11. 24920
    Prev
    Next
    INDEX
    Explanations

    terms related to ecological niches and species interactions within their habitats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dyn
    -0.16
     bq
    -0.15
    .mdl
    -0.15
    ç½²
    -0.15
    linger
    -0.14
     fauna
    -0.14
    ees
    -0.14
     dynasty
    -0.14
    Dyn
    -0.14
    ables
    -0.13
    POSITIVE LOGITS
    åĪĨå¸ĥ
    0.32
     habitat
    0.32
     distribution
    0.31
    distribution
    0.29
     distributions
    0.29
     habitats
    0.29
     Distribution
    0.28
    Distribution
    0.26
     Habit
    0.25
     range
    0.25
    Activations Density 0.116%

    No Known Activations