© 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. 31-LLAMASCOPE-RES-32K
    11. 30993
    Prev
    Next
    INDEX
    Explanations

    references to gods and historical figures related to warfare and art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eniz
    -0.13
    igram
    -0.13
    اسÙħ
    -0.13
    /callback
    -0.13
    iban
    -0.13
    ÑĢÑİ
    -0.12
    å¹ķ
    -0.12
    ä¹±
    -0.12
    εÏĩ
    -0.12
    angen
    -0.12
    POSITIVE LOGITS
     statue
    0.50
     statues
    0.48
     sculpture
    0.46
     sculptures
    0.44
     stat
    0.43
     sculpt
    0.42
     Statue
    0.41
     bronze
    0.40
     Sculpt
    0.40
     Stat
    0.39
    Activations Density 0.127%

    No Known Activations