INDEX

Explanations

terms related to apologies and expressions of regret

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

abouts

-0.15

egra

-0.15

vana

-0.15

 Fork

-0.15

 Hats

-0.14

iare

-0.14

mando

-0.14

ottage

-0.14

men

-0.14

 Norris

-0.13

POSITIVE LOGITS

znam

0.15

itm

0.14

ynomial

0.14

.factory

0.14

rint

0.14

pering

0.14

 perce

0.14

ì§ķ

0.13

æĹ§

0.13

OutOf

0.13

Activations Density 0.016%

terms related to apologies and expressions of regret

No Comments

No Known Activations