INDEX

Explanations

references to tourism-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

imen

-0.18

-0.15

 ç±

-0.15

ibre

-0.15

ossier

-0.15

ham

-0.14

Ĺ

-0.14

.foundation

-0.14

á»ĳ

-0.14

aret

-0.14

POSITIVE LOGITS

ovu

0.15

dale

0.14

vod

0.14

ÙĪØº

0.13

gev

0.13

.LENGTH

0.13

 Trot

0.13

çļĦåľ°

0.13

alley

0.13

Activations Density 0.016%

references to tourism-related content

No Comments

No Known Activations