INDEX

Explanations

terms and phrases related to exaggeration and amplification, particularly in a scientific or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

anik

-0.15

hani

-0.15

iw

-0.15

frey

-0.14

íĦ°

-0.14

 Dillon

-0.14

ering

-0.14

Ð»ÑĥÐ±

-0.14

áº¯c

-0.13

listener

-0.13

POSITIVE LOGITS

ically

0.19

bole

0.18

ìłģìĿ¸

0.16

ìłģìľ¼ë¡ľ

0.15

onymous

0.15

ologically

0.15

atisch

0.14

Recv

0.14

ound

0.14

urrect

0.14

Activations Density 0.337%

terms and phrases related to exaggeration and amplification, particularly in a scientific or technical context

No Comments

No Known Activations