© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 4-LLAMASCOPE-RES-32K
    11. 15086
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate evidence or proof related to actions and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arters
    -0.17
    jer
    -0.15
    vant
    -0.15
    ouch
    -0.15
    umont
    -0.15
    amba
    -0.15
    าà¸ģร
    -0.14
    ions
    -0.14
    vat
    -0.14
    enson
    -0.14
    POSITIVE LOGITS
     Francie
    0.15
     mode
    0.15
     broadly
    0.15
    bild
    0.15
    bilder
    0.14
     Mode
    0.14
    ê¶Į
    0.14
    ÇIJ
    0.14
     Abs
    0.14
    mode
    0.14
    Activations Density 0.330%

    No Known Activations