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. 18-LLAMASCOPE-RES-32K
    6. 16511
    Prev
    Next
    INDEX
    Explanations

    keywords related to leadership and agency dynamics in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bec
    -0.20
     Bec
    -0.18
     undert
    -0.15
     Podle
    -0.14
    лем
    -0.14
    imer
    -0.14
     når
    -0.13
     becomes
    -0.13
     ['-
    -0.13
    ASN
    -0.13
    POSITIVE LOGITS
     Äijang
    0.34
    æŃ£åľ¨
    0.30
    à¸ģำล
    0.25
    ãģ¦ãģĦãĤĭ
    0.21
    ãģĹãģ¦ãģĦãģ¾ãģĻ
    0.19
     está
    0.19
     are
    0.19
    ãģ¦ãģĦãģ¾ãģĻ
    0.18
     estão
    0.18
    ãģĦãģ¦ãģĦãĤĭ
    0.17
    Activations Density 0.613%

    No Known Activations