INDEX

Explanations

words associated with legal arguments or disputes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 bench

-0.17

gow

-0.16

rol

-0.16

 Benchmark

-0.15

cek

-0.15

ropa

-0.15

 Bench

-0.15

ROL

-0.15

rote

-0.14

cak

-0.14

POSITIVE LOGITS

okud

0.15

agers

0.15

ayer

0.15

Calibri

0.14

NullOrEmpty

0.14

ngu

0.14

eki

0.14

Ã©ri

0.14

Ã©ny

0.14

lerce

0.14

Activations Density 0.006%

words associated with legal arguments or disputes

No Comments

No Known Activations