INDEX

Explanations

conversational elements and greetings in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 -*-č↵

-0.14

 Homer

-0.14

âĶĺ

-0.14

izik

-0.13

esser

-0.13

romise

-0.13

oreal

-0.13

aise

-0.13

ently

-0.13

forgettable

-0.13

POSITIVE LOGITS

 hello

0.73

 Hello

0.70

Hello

0.62

hello

0.59

Hi

0.54

hi

0.53

_hello

0.50

Hi

0.49

 greeting

0.48

 greetings

0.46

Activations Density 0.283%

conversational elements and greetings in the text

No Comments

No Known Activations