Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 21101
    Prev
    Next
    INDEX
    Explanations

    themes related to dreams and their interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oron
    -0.14
    اصÙĦ
    -0.14
    773
    -0.14
     Kling
    -0.14
    .Listen
    -0.14
    imat
    -0.13
    DSL
    -0.13
    NamedQuery
    -0.13
     policy
    -0.13
    åľĪ
    -0.13
    POSITIVE LOGITS
     dream
    0.66
     Dream
    0.64
    Dream
    0.60
     dreams
    0.60
    dream
    0.59
     Dreams
    0.58
     dreaming
    0.58
    梦
    0.52
     dreamed
    0.52
    夢
    0.44
    Activations Density 0.081%

    No Known Activations