© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 11-LLAMASCOPE-RES-32K
    6. 29511
    Prev
    Next
    INDEX
    Explanations

    medical terms and information related to skin conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enia
    -0.15
    lime
    -0.15
    resh
    -0.15
    uft
    -0.14
    ssue
    -0.14
     ÑĥÑģл
    -0.14
    inha
    -0.14
    amak
    -0.14
    Ĩ
    -0.14
     Marble
    -0.14
    POSITIVE LOGITS
    zier
    0.17
     bordel
    0.17
    verted
    0.16
    iol
    0.16
    oplay
    0.15
     xamarin
    0.14
    441
    0.14
     didSelectRowAtIndexPath
    0.14
    Convertible
    0.14
     tip
    0.14
    Activations Density 0.116%

    No Known Activations