INDEX

Explanations

phrases indicating conditional situations or qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

odium

-0.18

uhn

-0.15

 bound

-0.15

ontrol

-0.14

ZE

-0.14

abinet

-0.14

rame

-0.14

 ÎĶÎµ

-0.14

 Bound

-0.14

_bound

-0.14

POSITIVE LOGITS

RelativeTo

0.16

 exclus

0.16

 cÄĥn

0.16

-o

0.15

xBC

0.15

 menn

0.15

apas

0.14

 nghiá»ĩp

0.14

ÑĨÐ°

0.14

 hosp

0.14

Activations Density 0.610%

phrases indicating conditional situations or qualifications

No Comments

No Known Activations