INDEX

Explanations

references to government actions regarding lawmaking and vetoes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oustic

-0.15

tual

-0.14

ulos

-0.14

ãĤ¤ãĤº

-0.14

ullan

-0.14

.experimental

-0.14

ãĥ¬ãĥ³

-0.14

spir

-0.13

umatic

-0.13

ocuk

-0.13

POSITIVE LOGITS

 Cabinet

0.17

Fur

0.15

-pad

0.15

fur

0.14

\xff

0.14

 cabinet

0.14

orest

0.14

fur

0.14

orem

0.14

 cabinets

0.13

Activations Density 0.036%

references to government actions regarding lawmaking and vetoes

No Comments

No Known Activations