© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 6641
    Prev
    Next
    INDEX
    Explanations

    instances of communication or responses in a conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HTTPRequest
    -0.14
    -Requested
    -0.13
    ÙĪØ·
    -0.13
    ·æĸ°
    -0.12
    Ç
    -0.12
    ôi
    -0.12
    ilan
    -0.12
    estone
    -0.12
    åĦĢ
    -0.12
    éļª
    -0.12
    POSITIVE LOGITS
     response
    1.07
     responses
    0.95
    response
    0.90
     reply
    0.90
     Response
    0.90
     respond
    0.89
     responded
    0.84
     responds
    0.83
     replies
    0.80
     Responses
    0.79
    Activations Density 0.804%

    No Known Activations