© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 13-LLAMASCOPE-RES-32K
    6. 25266
    Prev
    Next
    INDEX
    Explanations

    references to African countries and related health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÙĬÙĩ
    -0.17
    duit
    -0.16
    bung
    -0.15
    folio
    -0.15
    zk
    -0.14
    ugen
    -0.14
     Rim
    -0.14
    acting
    -0.14
    .ul
    -0.14
    bero
    -0.14
    POSITIVE LOGITS
    edes
    0.15
    é¢ij
    0.14
    emand
    0.14
     spinner
    0.14
    chaft
    0.14
     sm
    0.14
    .scalablytyped
    0.13
     accred
    0.13
    IGH
    0.13
     buses
    0.13
    Activations Density 0.160%

    No Known Activations