INDEX

Explanations

references to temporal phrases and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

edom

-0.16

Ð»Ð°Ð´Ñĥ

-0.15

 simply

-0.15

allen

-0.14

jar

-0.14

ÐµÐ¹

-0.13

omite

-0.13

MID

-0.13

er

-0.13

POSITIVE LOGITS

 simultaneously

0.19

-sama

0.15

IDD

0.15

aneously

0.15

oa

0.14

tee

0.14

 simult

0.14

_requires

0.14

rez

0.14

OWL

0.14

Activations Density 0.019%

references to temporal phrases and expressions

No Comments

No Known Activations