© 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. 28-LLAMASCOPE-RES-32K
    11. 22850
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific terms related to radar technology and antenna functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --
    -0.19
    regn
    -0.14
     âĪļ
    -0.14
    ãģĴ
    -0.14
    ping
    -0.14
    vrier
    -0.14
    éĽ²
    -0.13
     hak
    -0.13
    uko
    -0.13
    aeda
    -0.13
    POSITIVE LOGITS
    μβ
    0.16
    ipop
    0.14
    fork
    0.14
    essen
    0.14
    itas
    0.14
    .AnchorStyles
    0.14
    otas
    0.14
    ัà¸Ĺ
    0.13
    (())↵
    0.13
    вÑģÑı
    0.13
    Activations Density 0.043%

    No Known Activations