INDEX

Explanations

negative descriptions of actions or decisions

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

 desar

-0.19

aled

-0.16

_MAJOR

-0.15

phans

-0.15

ç²¾åĵģ

-0.14

ä¼į

-0.14

aud

-0.14

hz

-0.14

 Woodward

-0.14

åīĤ

-0.14

POSITIVE LOGITS

thest

0.16

Æ¡

0.15

ste

0.14

expo

0.14

mach

0.14

aken

0.14

Ø¯Ø§Ø±ÛĮ

0.14

stor

0.14

EST

0.13

asher

0.13

Activations Density 0.019%

negative descriptions of actions or decisions

No Comments

No Known Activations