INDEX

Explanations

formal statements of regret or apologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

asc

-0.17

 Solution

-0.15

.scalablytyped

-0.14

 Twitch

-0.14

acher

-0.14

qu

-0.14

adoo

-0.14

erten

-0.14

Wyn

-0.13

 revision

-0.13

POSITIVE LOGITS

ublik

0.15

inia

0.15

ìľ¡

0.14

 Ð¾Ð¿ÐµÑĢÐ°

0.14

arms

0.14

terra

0.14

posed

0.14

RESS

0.14

kanÄ±

0.14

tea

0.14

Activations Density 0.308%

formal statements of regret or apologies

No Comments

No Known Activations