INDEX

Explanations

words and phrases related to communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ÏĢÎ¬

-0.14

 impro

-0.14

 Guys

-0.13

roken

-0.13

ÐµÑĩ

-0.13

(!

-0.13

PRETTY

-0.13

bron

-0.13

ammen

-0.13

quires

-0.13

POSITIVE LOGITS

inu

0.16

uD

0.15

incerely

0.14

 Radiation

0.14

0.13

cid

0.13

oter

0.13

~~~~~~~~

0.13

[in

0.13

Activations Density 0.002%

words and phrases related to communication

No Comments

No Known Activations