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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 18542
    Prev
    Next
    INDEX
    Explanations

    references to health-related issues and their management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .gdx
    -0.15
    598
    -0.15
    èĽ
    -0.14
    ventus
    -0.13
    icus
    -0.13
    rdf
    -0.13
    /Runtime
    -0.12
    ulur
    -0.12
    缣
    -0.12
     Hindered
    -0.12
    POSITIVE LOGITS
     control
    1.22
    control
    1.07
     Control
    1.06
    -control
    1.05
    Control
    0.98
     controls
    0.95
     CONTROL
    0.94
    _control
    0.93
    æݧåĪ¶
    0.91
     controle
    0.90
    Activations Density 0.338%

    No Known Activations