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. 22945
    Prev
    Next
    INDEX
    Explanations

    Java collection and data structure elements

    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
     BitConverter
    -0.14
    thon
    -0.14
    135
    -0.13
     Majesty
    -0.13
    NamedQuery
    -0.13
     Urban
    -0.13
     Sovere
    -0.13
    fwrite
    -0.13
     Purple
    -0.13
    zee
    -0.12
    POSITIVE LOGITS
     String
    1.01
     string
    0.97
    String
    0.89
    -string
    0.88
     strings
    0.86
    string
    0.83
    _string
    0.81
     Strings
    0.79
     STRING
    0.79
    åŃĹ符串
    0.75
    Activations Density 0.323%

    No Known Activations