© 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. 12-LLAMASCOPE-RES-32K
    11. 14681
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions or actions that can be taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esson
    -0.18
    ModelProperty
    -0.17
    ote
    -0.15
    ouri
    -0.15
    LBL
    -0.14
    deme
    -0.14
    arden
    -0.14
    æºĸ
    -0.14
    fault
    -0.14
    æģĴ
    -0.14
    POSITIVE LOGITS
     freely
    0.23
    .fre
    0.15
    eldo
    0.15
    inox
    0.15
    åłĤ
    0.15
    å¯
    0.15
     Fre
    0.15
    &o
    0.15
    é¸
    0.14
    ÙħارÛĮ
    0.14
    Activations Density 0.371%

    No Known Activations