INDEX

Explanations

phrases indicating worry or concern

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

cles

-0.16

raid

-0.15

.sponge

-0.15

áº£o

-0.14

decess

-0.14

bli

-0.14

NC

-0.14

iado

-0.14

 ÙħÙħ

-0.14

IVEN

-0.14

POSITIVE LOGITS

ouch

0.17

Å¡ti

0.15

 worry

0.15

velle

0.15

ÙĪØ¹

0.15

immel

0.14

 Hlav

0.14

 spec

0.14

ÑĨÐµÐ½ÑĤÑĢÐ°

0.14

Activations Density 0.075%

phrases indicating worry or concern

No Comments

No Known Activations