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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 29-LLAMASCOPE-RES-32K
    6. 12420
    Prev
    Next
    INDEX
    Explanations

    references to various forms of death and associated themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ianne
    -0.15
     Dagger
    -0.15
    .catch
    -0.14
    ì°°
    -0.14
    inium
    -0.14
    dump
    -0.14
    stva
    -0.14
    .must
    -0.13
    odox
    -0.13
    etta
    -0.13
    POSITIVE LOGITS
     death
    0.87
    death
    0.71
     Death
    0.67
    -death
    0.64
    Death
    0.60
     deaths
    0.54
    _death
    0.50
     demise
    0.45
     DE
    0.44
    æŃ»äº¡
    0.43
    Activations Density 0.156%

    No Known Activations