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. 1-LLAMASCOPE-RES-32K
    6. 16316
    Prev
    Next
    INDEX
    Explanations

    the term "down" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odb
    -0.16
    iosper
    -0.15
    .simps
    -0.14
    allon
    -0.14
    kate
    -0.14
    Comparable
    -0.14
    tea
    -0.14
    anggal
    -0.14
    ãĥ¥ãĥ¼
    -0.14
    ãģĭãģªãģĦ
    -0.14
    POSITIVE LOGITS
     Weiner
    0.16
    ูà¹Ī
    0.15
    mad
    0.15
    éĺµ
    0.14
    played
    0.14
    ed
    0.14
     precip
    0.14
    mada
    0.14
    績
    0.14
     Lin
    0.14
    Activations Density 0.054%

    No Known Activations