© 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. 30-LLAMASCOPE-RES-32K
    11. 12258
    Prev
    Next
    INDEX
    Explanations

    terms related to commercial establishments and their operations

    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
     должна
    -0.48
     бÑĭла
    -0.46
     ÑģÑĤала
    -0.42
     italiana
    -0.41
     pública
    -0.39
     бÑĥла
    -0.39
     sola
    -0.38
     могла
    -0.38
     polÃŃtica
    -0.38
    “She
    -0.38
    POSITIVE LOGITS
    ativo
    0.26
    cido
    0.24
    ario
    0.24
    gado
    0.23
    iano
    0.23
    oso
    0.22
    ático
    0.22
    ertino
    0.22
    ónico
    0.22
    rico
    0.22
    Activations Density 0.204%

    No Known Activations