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. 6606
    Prev
    Next
    INDEX
    Explanations

    the name "Joel" with varying activation levels

    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
    avr
    -0.15
    lds
    -0.15
     Ing
    -0.14
     Millenn
    -0.14
    alat
    -0.14
    êm
    -0.14
    olut
    -0.13
    æļ®
    -0.13
    Audit
    -0.13
    ÑĢеж
    -0.13
    POSITIVE LOGITS
    оÑĢод
    0.17
    ivol
    0.16
    ignon
    0.15
    chio
    0.14
    تا
    0.14
    ToFit
    0.14
    ximo
    0.14
    cher
    0.14
    .radians
    0.14
    chos
    0.13
    Activations Density 0.013%

    No Known Activations