INDEX

Explanations

words associated with legal and bureaucratic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ocache

-0.18

è¯Ŀ

-0.17

 Prec

-0.15

_NC

-0.15

isay

-0.15

slash

-0.14

 ÑıÑģ

-0.14

spiracy

-0.14

inan

-0.14

POSITIVE LOGITS

ardi

0.19

ource

0.17

ammen

0.17

âĺħâĺħ

0.16

abor

0.15

viso

0.15

/pub

0.15

ze

0.14

zeit

0.14

ÑİÐº

0.14

Activations Density 0.083%

words associated with legal and bureaucratic contexts

No Comments

No Known Activations