INDEX

Explanations

the repeated phrase "around," indicating a focus on contexts or descriptions involving proximity or location

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

Negative Logits

QE

-0.17

Î¼ÎŃ

-0.16

ima

-0.16

ÏĥÏĦÎµ

-0.16

éłħ

-0.15

urb

-0.15

ÏĥÏī

-0.14

ownik

-0.14

yat

-0.14

jer

-0.13

POSITIVE LOGITS

erin

0.18

abouts

0.18

edReader

0.15

lopen

0.15

0.14

Ð»ÐºÐ¸

0.14

Î³ÎºÎµ

0.14

 kaldÄ±

0.14

beck

0.13

Ã¸j

0.13

Activations Density 0.042%

the repeated phrase "around," indicating a focus on contexts or descriptions involving proximity or location

No Known Activations