INDEX

Explanations

assertive statements and beliefs regarding brands, products, and social issues

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

rane

-0.18

ÑĮÐ¼Ð¸

-0.15

emes

-0.15

eyJ

-0.15

oke

-0.14

 ostat

-0.14

imeo

-0.14

 VÅ¡ech

-0.14

abis

-0.14

ichte

-0.14

POSITIVE LOGITS

 bout

0.16

HZ

0.15

éĢļãĤĬ

0.15

 chances

0.14

IVEN

0.14

 Transit

0.14

ç¦»

0.14

ONENT

0.13

/opt

0.13

Activations Density 0.252%

assertive statements and beliefs regarding brands, products, and social issues

No Comments

No Known Activations