INDEX

Explanations

instances of the word "among" and its variations, indicating a focus on group or collective 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

ising

-0.17

aries

-0.17

itz

-0.16

eri

-0.15

burg

-0.15

orsch

-0.14

ential

-0.14

eros

-0.14

osit

-0.13

oca

-0.13

POSITIVE LOGITS

st

0.36

 those

0.21

 Equals

0.20

 equals

0.20

 ÑģÐ¾Ð±Ð¾Ð¹

0.20

sted

0.19

est

0.19

 Ð¿ÑĢÐ¾Ñĩ

0.18

 themselves

0.18

Activations Density 0.033%

instances of the word "among" and its variations, indicating a focus on group or collective contexts

No Comments

No Known Activations