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. 3-LLAMASCOPE-RES-32K
    6. 23620
    Prev
    Next
    INDEX
    Explanations

    references to Nintendo and related gaming franchises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stoff
    -0.15
    ELLOW
    -0.15
    bote
    -0.14
    oure
    -0.14
    å·Ŀ
    -0.14
    dre
    -0.14
    plode
    -0.14
    å¥ı
    -0.14
    achten
    -0.14
    _Bool
    -0.14
    POSITIVE LOGITS
     flesh
    0.16
     FY
    0.15
    _periods
    0.15
     colonies
    0.15
    ke
    0.14
    itioner
    0.14
    itm
    0.14
    redient
    0.14
     ensl
    0.13
     Wolver
    0.13
    Activations Density 0.002%

    No Known Activations