© 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. 19738
    Prev
    Next
    INDEX
    Explanations

    ending patterns in words, particularly those ending with "er" or "edic" indicating various forms of action or characteristics

    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
    lical
    -0.16
     roman
    -0.16
    t
    -0.15
    east
    -0.15
    anned
    -0.15
    o
    -0.15
    anced
    -0.15
    sense
    -0.15
    eldon
    -0.15
    ariat
    -0.15
    POSITIVE LOGITS
    oded
    0.34
    oding
    0.27
    adic
    0.26
    asure
    0.24
    asers
    0.23
    aser
    0.21
    odes
    0.21
    asing
    0.21
    asures
    0.19
    ode
    0.19
    Activations Density 0.008%

    No Known Activations