© 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. 4-LLAMASCOPE-RES-32K
    11. 15182
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases and structures emphasizing "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     evidenced
    -0.17
    isku
    -0.17
    ìĬ¬
    -0.15
    Ñıк
    -0.15
    εÏį
    -0.15
    unami
    -0.14
    integration
    -0.14
    è°·
    -0.14
    linger
    -0.14
    uzey
    -0.14
    POSITIVE LOGITS
    paragus
    0.19
     well
    0.17
    ides
    0.16
    strup
    0.16
    haar
    0.16
    cribed
    0.16
     opposed
    0.15
    gard
    0.15
    usto
    0.15
    -built
    0.14
    Activations Density 0.324%

    No Known Activations