© 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. 24-LLAMASCOPE-RES-32K
    6. 8291
    Prev
    Next
    INDEX
    Explanations

    SQL statements related to table and column management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ظ
    -0.15
    cul
    -0.15
    ç½ijåĿĢ
    -0.14
    gon
    -0.14
     Sag
    -0.14
    ä¿Ĺ
    -0.14
    волÑı
    -0.14
    åĿĬ
    -0.13
    ne
    -0.13
     amt
    -0.13
    POSITIVE LOGITS
     product
    0.18
     contact
    0.18
     users
    0.18
     book
    0.17
     employee
    0.16
     employees
    0.16
     Contact
    0.16
    contact
    0.16
     lesson
    0.15
     person
    0.15
    Activations Density 0.388%

    No Known Activations