© 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. 10-LLAMASCOPE-RES-32K
    11. 10242
    Prev
    Next
    INDEX
    Explanations

    negative experiences related to brands and management practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Äįel
    -0.18
    gregar
    -0.15
    esis
    -0.15
    regor
    -0.15
    eddar
    -0.14
    ienes
    -0.14
    alic
    -0.14
    人人
    -0.14
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.14
     Stewart
    -0.14
    POSITIVE LOGITS
     privat
    0.14
    dis
    0.14
    acher
    0.14
    anco
    0.14
    reo
    0.14
    vas
    0.14
    .parseInt
    0.14
    iro
    0.13
    ë¹ł
    0.13
     lou
    0.13
    Activations Density 0.476%

    No Known Activations