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. 14213
    Prev
    Next
    INDEX
    Explanations

    cooking-related instructions and ingredients

    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
    apia
    -0.16
    ebin
    -0.14
    bia
    -0.14
    aney
    -0.14
    OperationException
    -0.14
    .lab
    -0.14
    ampo
    -0.14
    oodle
    -0.14
    intendo
    -0.14
    .scalablytyped
    -0.14
    POSITIVE LOGITS
    eri
    0.16
    sson
    0.15
    uba
    0.15
     Burb
    0.15
    ague
    0.15
     Tradable
    0.14
    lon
    0.14
    uchs
    0.14
    exe
    0.14
     crown
    0.14
    Activations Density 0.033%

    No Known Activations