INDEX

Explanations

phrases that indicate strong opinions or high praise about something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Postal

-0.15

ooth

-0.14

age

-0.14

ugh

-0.14

atl

-0.14

 Posts

-0.14

 Personnel

-0.14

Sal

-0.14

POSITIVE LOGITS

uniacid

0.16

_CNTL

0.15

rani

0.15

urator

0.15

anness

0.15

ÙĨØ¹

0.15

ÐĶÐļ

0.15

jom

0.15

_dw

0.14

asma

0.14

Activations Density 0.721%

phrases that indicate strong opinions or high praise about something

No Comments

No Known Activations