© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 6-LLAMASCOPE-RES-32K
    11. 25417
    Prev
    Next
    INDEX
    Explanations

    statements related to assumptions and considerations in theoretical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aget
    -0.16
    алов
    -0.15
    ½æķ°
    -0.14
    ников
    -0.14
    appers
    -0.14
    metro
    -0.14
    aton
    -0.14
    fcn
    -0.14
    stead
    -0.13
    aston
    -0.13
    POSITIVE LOGITS
    ingham
    0.16
    309
    0.15
    885
    0.15
    316
    0.15
     Schneider
    0.15
     Abrams
    0.14
    809
    0.14
    276
    0.14
    919
    0.14
    317
    0.13
    Activations Density 0.076%

    No Known Activations