© 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. 4989
    Prev
    Next
    INDEX
    Explanations

    expressions of encouragement and advice, particularly related to personal growth and pursuing opportunities

    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
    uto
    -0.14
     Estr
    -0.14
    StackNavigator
    -0.13
    _FC
    -0.13
    ç¤
    -0.13
     Zá
    -0.13
     requestOptions
    -0.13
    à¹Ģห
    -0.12
    éijij
    -0.12
    opup
    -0.12
    POSITIVE LOGITS
     don
    0.51
    don
    0.42
    Don
    0.37
     Don
    0.36
     DON
    0.34
     dont
    0.33
    DON
    0.31
    _don
    0.30
    dont
    0.28
    ä¸įè¦ģ
    0.28
    Activations Density 0.589%

    No Known Activations