© 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. 22-LLAMASCOPE-RES-32K
    11. 20216
    Prev
    Next
    INDEX
    Explanations

    mentions of spiritual care and support services in healthcare contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /"
    -0.15
     .↵↵↵↵
    -0.15
     ("
    -0.14
    /'
    -0.14
    [this
    -0.14
    istrovstvÃŃ
    -0.14
    ,this
    -0.13
    еÑĢÑĪ
    -0.13
    åı¦
    -0.13
    uÄį
    -0.12
    POSITIVE LOGITS
    :↵
    0.75
    :↵↵
    0.58
    :č↵
    0.56
    :
    0.50
     :↵
    0.50
    :</
    0.48
    ):↵
    0.47
    ï¼ļ↵
    0.46
    :↵↵↵
    0.45
    :");↵
    0.44
    Activations Density 0.593%

    No Known Activations