INDEX

Explanations

references to significant events or achievements in the context of performance and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

unl

-0.15

Ð¾Ð³Ð¾Ð´

-0.15

orris

-0.15

orge

-0.14

ighthouse

-0.14

Corp

-0.14

ç·

-0.14

æ¦

-0.14

BY

-0.14

æĺİ

-0.14

POSITIVE LOGITS

et

0.16

etur

0.16

 full

0.15

ija

0.14

ÐºÐ¾Ð´

0.14

DM

0.14

 federally

0.13

 amount

0.13

 single

0.13

WISE

0.13

Activations Density 0.214%

references to significant events or achievements in the context of performance and recognition

No Comments

No Known Activations