© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 2-LLAMASCOPE-RES-32K
    11. 25435
    Prev
    Next
    INDEX
    Explanations

    references to the act of polishing or items that are polished

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pire
    -0.17
     Thornton
    -0.16
    azine
    -0.16
     bufsize
    -0.15
    azines
    -0.15
    emer
    -0.14
    INY
    -0.14
     Teh
    -0.14
     Greenwich
    -0.14
    ecute
    -0.14
    POSITIVE LOGITS
    ardo
    0.17
    etta
    0.15
    andest
    0.15
    ocoder
    0.15
    Expose
    0.15
    alie
    0.15
    asio
    0.15
    atr
    0.15
    æĽ
    0.14
    stered
    0.14
    Activations Density 0.022%

    No Known Activations