© 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. 18-LLAMASCOPE-RES-32K
    11. 12787
    Prev
    Next
    INDEX
    Explanations

    themes related to community challenges and public accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anzi
    -0.14
    ä¸ĢåĪĩ
    -0.14
    å®ĥ
    -0.14
    asant
    -0.13
    ensive
    -0.13
    vant
    -0.13
    etooth
    -0.13
    QUENCE
    -0.13
    زاÙĨ
    -0.13
    ampion
    -0.13
    POSITIVE LOGITS
     some
    0.44
     many
    0.40
    some
    0.38
     majority
    0.38
    many
    0.34
    æľīçļĦ
    0.34
     Some
    0.34
     ones
    0.32
    æľīäºĽ
    0.30
    Some
    0.30
    Activations Density 0.698%

    No Known Activations