© 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. 1628
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly prominent figures mentioned by name

    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
    roti
    -0.15
    lug
    -0.15
    quam
    -0.14
    ãĥ¼ãĥĦ
    -0.14
    fik
    -0.14
    emailer
    -0.14
    _Component
    -0.14
    .PrimaryKey
    -0.14
    ppo
    -0.14
    Æ
    -0.14
    POSITIVE LOGITS
    501
    0.16
     SHR
    0.15
     deduct
    0.14
     deduction
    0.14
    raÄį
    0.14
    803
    0.14
    inet
    0.14
     æij
    0.14
    counter
    0.14
    itech
    0.14
    Activations Density 0.345%

    No Known Activations