INDEX

Explanations

occurrences of the word "The" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

yer

-0.17

ndon

-0.14

éĤ¦

-0.14

yers

-0.14

ceed

-0.14

Ð´ÐµÐ¼

-0.14

weit

-0.14

undle

-0.14

etro

-0.14

itest

-0.14

POSITIVE LOGITS

undef

0.19

atre

0.17

ewan

0.16

jc

0.15

 Stra

0.15

 Wire

0.15

disposing

0.15

ISTR

0.15

atl

0.15

 Hill

0.15

Activations Density 0.041%

occurrences of the word "The" and its variations in different contexts

No Comments

No Known Activations