© 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. 29-LLAMASCOPE-RES-32K
    11. 3649
    Prev
    Next
    INDEX
    Explanations

    details about personal experiences and background

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stab
    -0.19
    imi
    -0.17
     stabil
    -0.16
     Saud
    -0.16
    lei
    -0.16
    JI
    -0.15
    adora
    -0.15
     Sask
    -0.15
    enger
    -0.15
     Stable
    -0.15
    POSITIVE LOGITS
     Steve
    1.15
    Steve
    1.02
     Steven
    0.95
     STE
    0.85
     ste
    0.85
    Steven
    0.82
     Stephen
    0.78
    STE
    0.77
    ste
    0.68
     Stevens
    0.68
    Activations Density 0.052%

    No Known Activations