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. 16-LLAMASCOPE-RES-32K
    6. 1514
    Prev
    Next
    INDEX
    Explanations

    details related to political positions and electoral districts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perfor
    -0.14
     Siege
    -0.14
    ieber
    -0.14
     stud
    -0.13
     Institute
    -0.13
    adb
    -0.13
    vf
    -0.13
    otre
    -0.13
    uty
    -0.13
    .idea
    -0.13
    POSITIVE LOGITS
     district
    0.17
    'gc
    0.17
     District
    0.16
    ãĥ³ãĤ°ãĥ«
    0.15
    umes
    0.15
    District
    0.15
     Furn
    0.15
    ingle
    0.15
    uliar
    0.15
    åĽ
    0.14
    Activations Density 0.148%

    No Known Activations