INDEX

Explanations

legal terminology and references to analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ynes

-0.18

-0.16

kre

-0.14

 kÄ±s

-0.14

Invariant

-0.14

loÅ¾

-0.14

Ìģc

-0.13

igue

-0.13

.inst

-0.13

 Schmidt

-0.13

POSITIVE LOGITS

AGR

0.16

 UPDATED

0.15

ÐºÐ°Ñģ

0.14

Zug

0.14

actly

0.14

nown

0.14

untime

0.14

 Cron

0.14

/topic

0.14

usat

0.13

Activations Density 0.181%

legal terminology and references to analysis

No Comments

No Known Activations