© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 2416
    Prev
    Next
    INDEX
    Explanations

    references to the name "Nelson."

    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
    ystack
    -0.16
    διά
    -0.16
    ži
    -0.16
    abi
    -0.16
    ingham
    -0.15
    eldon
    -0.15
    eway
    -0.14
     sứ
    -0.14
    elper
    -0.14
    uchos
    -0.14
    POSITIVE LOGITS
     Mandela
    0.20
    andest
    0.17
    atrix
    0.16
    rollo
    0.16
    UME
    0.14
    ाप
    0.14
    (Network
    0.14
    acro
    0.14
    wick
    0.14
    ites
    0.14
    Activations Density 0.016%

    No Known Activations