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. 29-LLAMASCOPE-RES-32K
    6. 3858
    Prev
    Next
    INDEX
    Explanations

    phrases and responses involving communication and replies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    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
    -0.17
    -Requested
    -0.13
    csi
    -0.13
    etri
    -0.13
    /Runtime
    -0.13
    ôi
    -0.13
    ChangeEvent
    -0.13
    ogh
    -0.12
     Razor
    -0.12
    RIX
    -0.12
    POSITIVE LOGITS
     response
    0.98
     responses
    0.85
     reply
    0.85
     respond
    0.83
    response
    0.83
     Response
    0.81
     responds
    0.78
     responded
    0.77
     answer
    0.76
     réponse
    0.75
    Activations Density 0.657%

    No Known Activations