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. 12-LLAMASCOPE-RES-32K
    6. 5925
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purposes or functions associated with various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ties
    -0.17
    adele
    -0.16
    ilm
    -0.15
    mh
    -0.15
    ka
    -0.15
    usercontent
    -0.15
    mite
    -0.15
    andard
    -0.14
    alia
    -0.14
    mia
    -0.14
    POSITIVE LOGITS
     sake
    0.29
    geries
    0.29
    -profit
    0.28
    bidden
    0.27
     purposes
    0.24
     instance
    0.24
    aging
    0.23
    feit
    0.23
    /by
    0.23
    wards
    0.20
    Activations Density 0.722%

    No Known Activations