INDEX

Explanations

the repeated use of the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ãģĤãĤĭ

-0.23

ãģĤãĤĬ

-0.23

ãģĤãģ£ãģŁ

-0.19

idon

-0.17

sic

-0.17

iy

-0.16

ãģĬ

-0.15

rone

-0.14

icens

-0.14

POSITIVE LOGITS

ched

0.30

ching

0.29

ch

0.21

upon

0.21

ches

0.21

chy

0.20

away

0.19

soever

0.18

éº¼

0.18

-Ð½Ð¸Ð±ÑĥÐ´ÑĮ

0.17

Activations Density 0.257%

the repeated use of the word "that" in various contexts

No Comments

No Known Activations