© 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. 23-LLAMASCOPE-RES-32K
    6. 20872
    Prev
    Next
    INDEX
    Explanations

    mentions of black-and-white or vintage photographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ixer
    -0.17
    oplast
    -0.15
    idth
    -0.15
    ระ
    -0.14
    702
    -0.13
     Gold
    -0.13
    šov
    -0.13
    nemonic
    -0.13
    обов
    -0.13
    åħ½
    -0.13
    POSITIVE LOGITS
     black
    0.69
    black
    0.57
    é»ij
    0.54
     blacks
    0.47
     é»ij
    0.45
    -black
    0.45
     BLACK
    0.44
     mon
    0.44
     Black
    0.43
    .black
    0.41
    Activations Density 0.107%

    No Known Activations