INDEX

Explanations

references to Oprah Winfrey and her brand

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

edic

-0.15

ewed

-0.15

 UsersController

-0.15

orpion

-0.14

arkin

-0.14

ahat

-0.14

arios

-0.14

bris

-0.14

estone

-0.14

ikut

-0.13

POSITIVE LOGITS

HORT

0.17

 Horton

0.15

Probe

0.14

thren

0.14

ioni

0.14

closure

0.14

 Sachs

0.14

ibern

0.14

 closure

0.13

chest

0.13

Activations Density 0.006%

references to Oprah Winfrey and her brand

No Comments

No Known Activations