© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 15530
    Prev
    Next
    INDEX
    Explanations

    entities and proper nouns related to locations and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iteli
    -0.19
    unga
    -0.19
    NZ
    -0.18
     Rajasthan
    -0.17
     Auckland
    -0.17
     Fiji
    -0.16
     Fargo
    -0.16
    uze
    -0.16
     Idaho
    -0.16
    grese
    -0.16
    POSITIVE LOGITS
     Maryland
    0.82
     Baltimore
    0.77
     Md
    0.58
     Orioles
    0.56
    altimore
    0.54
    Md
    0.47
     MD
    0.46
     mary
    0.46
    Mary
    0.45
     Ches
    0.45
    Activations Density 0.178%

    No Known Activations