INDEX

Explanations

negations or expressions of uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

trand

-0.15

 Trophy

-0.14

 Strict

-0.14

 Rena

-0.14

thren

-0.14

Ŀ

-0.14

Ð³Ð¾

-0.14

POSITIVE LOGITS

engin

0.17

MBER

0.17

asher

0.16

 Quint

0.16

dash

0.15

igkeit

0.14

icina

0.14

Å¾el

0.14

ahlen

0.14

æ©

0.14

Activations Density 0.184%

negations or expressions of uncertainty

No Comments

No Known Activations