INDEX

Explanations

references to search engines and their associated algorithms or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Franc

-0.15

itus

-0.15

itas

-0.14

laughter

-0.14

 franc

-0.14

hus

-0.14

bs

-0.14

adm

-0.14

andy

-0.14

alary

-0.14

POSITIVE LOGITS

jde

0.15

 chá»¯

0.15

_PHASE

0.14

gu

0.14

atables

0.14

iesen

0.14

Phase

0.14

 lief

0.14

 ÑģÐ¾Ñĩ

0.14

elite

0.13

Activations Density 0.015%

references to search engines and their associated algorithms or results

No Comments

No Known Activations