INDEX

Explanations

phrases indicating location or place

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

(___

-0.15

 sposÃ³b

-0.15

icket

-0.14

 ustanov

-0.14

atos

-0.14

zac

-0.14

 Victim

-0.14

 behalf

-0.14

 ì¹

-0.13

arto

-0.13

POSITIVE LOGITS

tie

0.17

obl

0.16

upon

0.15

etrofit

0.14

Tie

0.14

essler

0.14

tie

0.14

vider

0.14

pires

0.14

uell

0.14

Activations Density 0.037%

phrases indicating location or place

No Comments

No Known Activations