© 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. 2-LLAMASCOPE-RES-32K
    11. 16454
    Prev
    Next
    INDEX
    Explanations

    terms related to carrying or transporting items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rips
    -0.16
    rego
    -0.14
    blas
    -0.14
    /Foundation
    -0.14
    alle
    -0.14
    ALLE
    -0.13
    AMES
    -0.13
     reels
    -0.13
    src
    -0.13
    ucas
    -0.13
    POSITIVE LOGITS
     Orr
    0.17
    LLL
    0.17
    apan
    0.15
    erry
    0.14
    icone
    0.14
    inge
    0.14
    aucoup
    0.14
    ull
    0.14
    aterno
    0.14
    ικα
    0.14
    Activations Density 0.011%

    No Known Activations