© 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. 13-LLAMASCOPE-RES-32K
    11. 16740
    Prev
    Next
    INDEX
    Explanations

    phrases indicating academic or research excellence, classifications, and levels of achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kız
    -0.17
    ocz
    -0.15
    .Atomic
    -0.15
     (!((
    -0.15
    ãĤ¤ãĤº
    -0.14
    ngx
    -0.14
    产
    -0.14
    ÑĥÑĢи
    -0.14
    ApplicationBuilder
    -0.13
    SetName
    -0.13
    POSITIVE LOGITS
    885
    0.17
    ial
    0.15
    ialized
    0.14
    *****↵↵
    0.14
    ubs
    0.14
     level
    0.14
    enthal
    0.14
    ť
    0.14
     Moran
    0.13
     reserve
    0.13
    Activations Density 0.049%

    No Known Activations