INDEX

Explanations

phrases indicating competence or qualifications 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

chine

-0.15

.dm

-0.14

formace

-0.14

liner

-0.14

ï»¿#

-0.14

krom

-0.14

nothrow

-0.14

VOKE

-0.13

pty

-0.13

werk

-0.13

POSITIVE LOGITS

 poised

0.30

-position

0.30

 positioned

0.29

-su

0.28

 suited

0.28

 situated

0.28

 equipped

0.27

-equipped

0.26

 able

0.25

-po

0.25

Activations Density 0.036%

phrases indicating competence or qualifications in various contexts

No Comments

No Known Activations