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. 9-LLAMASCOPE-RES-32K
    6. 4384
    Prev
    Next
    INDEX
    Explanations

    key terms and identifiers from programming and technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jour
    -0.15
    linger
    -0.15
    ilton
    -0.14
     leds
    -0.14
    illo
    -0.14
     æ°
    -0.14
     depress
    -0.14
    jours
    -0.14
    quist
    -0.14
    /cms
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĥª
    0.18
    ecal
    0.16
    147
    0.15
    ounder
    0.15
    allee
    0.15
    783
    0.15
    çĸ¾
    0.14
    urm
    0.14
    oupon
    0.14
    275
    0.14
    Activations Density 0.003%

    No Known Activations