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. 2-LLAMASCOPE-RES-32K
    6. 21939
    Prev
    Next
    INDEX
    Explanations

    references to document citations or publication years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wap
    -0.15
    aims
    -0.14
    ister
    -0.14
     Bez
    -0.14
     ash
    -0.14
     vers
    -0.14
    HUD
    -0.14
    ersed
    -0.14
    çī§
    -0.14
    ((↵
    -0.14
    POSITIVE LOGITS
    ãģĭãģ£ãģ¦
    0.15
    .Debugger
    0.15
    utow
    0.14
    883
    0.14
    anst
    0.14
    arkers
    0.14
    utin
    0.14
    uali
    0.14
    876
    0.14
    885
    0.14
    Activations Density 0.007%

    No Known Activations