© 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. 12-LLAMASCOPE-RES-32K
    11. 6129
    Prev
    Next
    INDEX
    Explanations

    mentions of featured artists or collaborations in music-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usercontent
    -0.17
    aller
    -0.17
     ä»·æł¼
    -0.15
    ãĤ¡
    -0.15
    pollo
    -0.15
     uranus
    -0.15
    ibri
    -0.14
    abay
    -0.14
    CLE
    -0.14
    enor
    -0.14
    POSITIVE LOGITS
    907
    0.16
    946
    0.16
     rol
    0.15
     Doctor
    0.14
     Amen
    0.14
    808
    0.14
     rolling
    0.13
    -Sah
    0.13
     offset
    0.13
    ожеÑĤ
    0.13
    Activations Density 0.003%

    No Known Activations