INDEX

Explanations

words or phrases that indicate conditions, clauses, or combinations in legal or contractual contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

gles

-0.17

uku

-0.16

emet

-0.15

urma

-0.15

 claro

-0.15

uracy

-0.14

icious

-0.14

.rm

-0.14

abant

-0.14

ujet

-0.14

POSITIVE LOGITS

 Bris

0.15

ippo

0.14

pole

0.14

 Ð¿Ð»Ð°ÑģÑĤÐ¸

0.14

ritten

0.14

Ein

0.13

#ad

0.13

icer

0.13

(firstName

0.13

 Mack

0.13

Activations Density 0.153%

words or phrases that indicate conditions, clauses, or combinations in legal or contractual contexts

No Comments

No Known Activations