© 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. 30815
    Prev
    Next
    INDEX
    Explanations

    concepts related to sustainability and innovation in building design

    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
     Charleston
    -0.17
     Belize
    -0.16
    ubre
    -0.15
     Clifford
    -0.15
     Montgomery
    -0.14
    icut
    -0.14
    566
    -0.14
     Georgetown
    -0.14
    platz
    -0.14
     Sherman
    -0.14
    POSITIVE LOGITS
     Finnish
    0.56
     Finland
    0.54
     Helsinki
    0.52
    .fi
    0.42
     Finn
    0.38
     Ãħ
    0.34
     Nordic
    0.34
     Fin
    0.34
    Fin
    0.33
     Nokia
    0.33
    Activations Density 0.098%

    No Known Activations