© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 17672
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CIM
    -0.15
    igo
    -0.15
    ValueCollection
    -0.14
    inox
    -0.14
    IGO
    -0.14
     Verm
    -0.14
    coin
    -0.13
    ertil
    -0.13
    aler
    -0.13
    OrDefault
    -0.13
    POSITIVE LOGITS
     first
    0.30
    第ä¸Ģ次
    0.27
    first
    0.24
     eerste
    0.23
     첫
    0.23
     prvnÃŃ
    0.22
     første
    0.22
     erste
    0.22
     pierws
    0.21
    à¹ģรà¸ģ
    0.21
    Activations Density 0.065%

    No Known Activations