Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 2121
    Prev
    Next
    INDEX
    Explanations

    elements associated with cultural identity and tradition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANNEL
    -0.18
     maduras
    -0.17
    ä¸Ī
    -0.17
    ãĤ«ãĥ¼
    -0.16
    652
    -0.16
    lok
    -0.15
    gy
    -0.15
    085
    -0.14
    AtA
    -0.14
    abilidade
    -0.14
    POSITIVE LOGITS
    oppel
    0.19
    itos
    0.18
    ë§Ŀ
    0.17
    zac
    0.17
    aced
    0.16
     Gu
    0.16
     del
    0.16
    andin
    0.16
    orest
    0.15
    ÑĢеÑħ
    0.15
    Activations Density 0.557%

    No Known Activations