© 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. 10978
    Prev
    Next
    INDEX
    Explanations

    references to saints or holy figures

    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
    Å¡ov
    -0.15
    razione
    -0.15
    usalem
    -0.15
    heet
    -0.14
    -mouth
    -0.14
    warm
    -0.14
    IGHL
    -0.14
     mrb
    -0.14
    à¤Ĺल
    -0.14
    ContentLoaded
    -0.14
    POSITIVE LOGITS
     Exped
    0.22
     Ther
    0.20
    igmatic
    0.20
    igm
    0.19
     Corona
    0.19
    ational
    0.18
     Pad
    0.18
     Brid
    0.18
    igmat
    0.17
     Bir
    0.17
    Activations Density 0.022%

    No Known Activations