© 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. 24-LLAMASCOPE-RES-32K
    11. 7432
    Prev
    Next
    INDEX
    Explanations

    references to company history and experience

    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
    insky
    -0.16
     Reality
    -0.14
     mainstream
    -0.13
    çĿ£
    -0.13
     emerging
    -0.13
     Composition
    -0.12
     freeing
    -0.12
    orough
    -0.12
     Redemption
    -0.12
     Bye
    -0.12
    POSITIVE LOGITS
     tradition
    0.31
     century
    0.30
     generations
    0.27
     heritage
    0.25
     traditions
    0.25
     Tradition
    0.24
     history
    0.23
     decades
    0.22
     legacy
    0.22
     centuries
    0.22
    Activations Density 0.168%

    No Known Activations