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. 16-LLAMASCOPE-RES-32K
    6. 22009
    Prev
    Next
    INDEX
    Explanations

    key statistical data and comparisons related to societal trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aN
    -0.15
    ady
    -0.14
    porn
    -0.14
     discrepan
    -0.14
    abella
    -0.13
    ade
    -0.13
    лик
    -0.13
    à¤Ł
    -0.13
    atomy
    -0.13
    å«
    -0.13
    POSITIVE LOGITS
     according
    0.38
    according
    0.31
     According
    0.30
     report
    0.29
    According
    0.29
     Report
    0.24
    ccording
    0.24
     según
    0.23
     analysis
    0.22
     studies
    0.22
    Activations Density 0.288%

    No Known Activations