© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 25876
    Prev
    Next
    INDEX
    Explanations

    references to important concepts or ideas denoted by "key" or "key points."

    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
    KeyName
    -0.18
    _key
    -0.18
    KeyEvent
    -0.17
    Key
    -0.17
    KEY
    -0.17
    ickers
    -0.16
    key
    -0.16
    KeyDown
    -0.15
    _via
    -0.15
     key
    -0.15
    POSITIVE LOGITS
    hole
    0.39
    notes
    0.36
    note
    0.33
    chain
    0.29
    holes
    0.27
    -note
    0.27
     players
    0.26
    chains
    0.25
    cloak
    0.25
    lime
    0.24
    Activations Density 0.021%

    No Known Activations