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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12-LLAMASCOPE-RES-32K
    6. 14892
    Prev
    Next
    INDEX
    Explanations

    references to specific districts or districts in a legal or educational context

    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
    erals
    -0.15
    itz
    -0.15
    eral
    -0.15
    itable
    -0.15
    leigh
    -0.14
    ISTER
    -0.14
    ترÛĮ
    -0.14
    ÑĮми
    -0.14
    essler
    -0.14
     ÑģкладÑĥ
    -0.13
    POSITIVE LOGITS
    wide
    0.23
    -wide
    0.22
    arian
    0.20
    arians
    0.20
     же
    0.18
    naire
    0.18
    ively
    0.18
    ted
    0.17
    /state
    0.17
    ships
    0.17
    Activations Density 0.034%

    No Known Activations