Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 5519
    Prev
    Next
    INDEX
    Explanations

    terms related to art and artistic assessment

    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
    qml
    -0.17
    oui
    -0.15
    ÌĤ
    -0.15
    ãģªãģĬ
    -0.15
     Ende
    -0.14
    ιÏĥÏĦή
    -0.14
    847
    -0.14
    ACES
    -0.14
    izik
    -0.14
     Encoder
    -0.14
    POSITIVE LOGITS
     é
    0.99
    é
    0.91
    Ãī
    0.78
     Ãī
    0.67
    è
    0.66
    &eacute
    0.62
     è
    0.59
    'é
    0.57
    ’é
    0.57
    ÃĪ
    0.49
    Activations Density 0.151%

    No Known Activations