Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 29522
    Prev
    Next
    INDEX
    Explanations

    mentions of camera equipment or photography-related terms

    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
    otland
    -0.16
    MBER
    -0.15
     substance
    -0.14
    ashboard
    -0.14
    uml
    -0.13
     sher
    -0.13
     Crossing
    -0.13
    stroy
    -0.13
     ÑĢÑĥб
    -0.13
    èIJ½ãģ¡
    -0.13
    POSITIVE LOGITS
    èªł
    0.15
    erot
    0.15
     Barnett
    0.15
    teness
    0.14
     Twin
    0.14
    aturas
    0.14
    erez
    0.14
    eros
    0.14
    andler
    0.14
    reon
    0.14
    Activations Density 0.002%

    No Known Activations