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. 2272
    Prev
    Next
    INDEX
    Explanations

    references to Russian interference in elections and related investigations

    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
    pter
    -0.16
    PropertyValue
    -0.16
    lix
    -0.15
    ////////////////////////////////////////////////////
    -0.15
    veau
    -0.15
    raman
    -0.14
    _sampling
    -0.14
    lý
    -0.14
    /Private
    -0.14
    pute
    -0.14
    POSITIVE LOGITS
     Ard
    0.15
    iego
    0.15
    contro
    0.15
    à¹Ħว
    0.14
    /fw
    0.14
     Proud
    0.14
    /bower
    0.14
    Ay
    0.14
     Ay
    0.14
    utomation
    0.14
    Activations Density 0.011%

    No Known Activations