© 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. 8-LLAMASCOPE-RES-32K
    11. 30840
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate continuity or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abin
    -0.15
    osu
    -0.14
    ac
    -0.14
    /from
    -0.14
    abyrin
    -0.14
    sein
    -0.14
    acia
    -0.13
    ula
    -0.13
     Settlement
    -0.13
    phe
    -0.13
    POSITIVE LOGITS
    ders
    0.22
    íģ¼
    0.16
    LEGAL
    0.16
    ickers
    0.15
    ainen
    0.15
    812
    0.15
    opal
    0.15
    CHANT
    0.14
    nings
    0.14
    nech
    0.14
    Activations Density 0.027%

    No Known Activations