© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 10888
    Prev
    Next
    INDEX
    Explanations

    specific anatomical descriptions related to wing structure in insects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _requires
    -0.15
    é³´
    -0.15
     ilma
    -0.15
    rieve
    -0.14
    iber
    -0.14
    iqu
    -0.14
    bero
    -0.14
     пода
    -0.14
    IDER
    -0.14
     коÑĢп
    -0.14
    POSITIVE LOGITS
    ForRow
    0.17
     recur
    0.16
     unarmed
    0.16
     marginal
    0.16
     weak
    0.16
     club
    0.16
     vest
    0.15
     fee
    0.15
     ke
    0.15
    Gran
    0.15
    Activations Density 0.015%

    No Known Activations