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. 15-LLAMASCOPE-RES-32K
    6. 19208
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal feelings and desires towards others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ìĿ´ìĬ¤
    -0.15
    تاÙĨ
    -0.15
    amespace
    -0.15
    ĵ¨
    -0.15
    rado
    -0.15
    -FIRST
    -0.14
    ût
    -0.14
    CFG
    -0.14
    OTAL
    -0.14
    velle
    -0.14
    POSITIVE LOGITS
     feel
    0.21
    /us
    0.17
     sense
    0.17
    uman
    0.16
     available
    0.16
     aware
    0.15
    ubb
    0.15
     sure
    0.15
     subject
    0.15
     Impress
    0.15
    Activations Density 0.027%

    No Known Activations