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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27151
    Prev
    Next
    INDEX
    Explanations

    discussions about moral dilemmas and ethical implications

    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
    erras
    -0.16
    ar
    -0.16
    stadt
    -0.15
    ensing
    -0.15
    ayi
    -0.15
    ãģĤãģĴ
    -0.14
    pping
    -0.13
     nar
    -0.13
    nik
    -0.13
    anc
    -0.13
    POSITIVE LOGITS
     having
    0.24
     simply
    0.19
     spending
    0.18
     doing
    0.18
     setting
    0.17
     holding
    0.17
     letting
    0.17
     taking
    0.17
     unlink
    0.16
     getting
    0.16
    Activations Density 0.662%

    No Known Activations