INDEX

Explanations

instances of the word "moved" and related terms indicating relocation or transition

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

alendar

-0.16

amus

-0.15

rek

-0.15

arya

-0.14

ene

-0.14

ENE

-0.14

lein

-0.14

ãģ¯ãģļ

-0.14

rans

-0.14

iegel

-0.14

POSITIVE LOGITS

 away

0.23

 permanently

0.20

 onto

0.19

 into

0.19

 cities

0.17

 khá»ıi

0.17

Cities

0.17

_into

0.15

 Away

0.15

olle

0.15

Activations Density 0.024%

instances of the word "moved" and related terms indicating relocation or transition

No Comments

No Known Activations