© 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. 12732
    Prev
    Next
    INDEX
    Explanations

    phrases that describe potential risks or dangers

    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
    arend
    -0.16
     NÄĽkter
    -0.15
     Shared
    -0.15
    ietet
    -0.14
     Canter
    -0.14
    rif
    -0.14
    TEGER
    -0.14
     Podle
    -0.13
    atif
    -0.13
    _vlog
    -0.13
    POSITIVE LOGITS
     combination
    0.69
     combined
    0.59
     combine
    0.59
    combination
    0.56
     combo
    0.55
    combined
    0.54
     Combination
    0.53
     Combine
    0.52
     combinations
    0.52
    Combine
    0.50
    Activations Density 0.462%

    No Known Activations