INDEX

Explanations

references to flashbacks or related terms in narrative contexts

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

unan

-0.16

ctest

-0.15

uez

-0.15

tsx

-0.15

isel

-0.15

urma

-0.15

å±±å¸Ĥ

-0.14

ooter

-0.14

ibar

-0.14

 giant

-0.13

POSITIVE LOGITS

eroon

0.16

adel

0.15

btc

0.15

Erd

0.15

LOCKS

0.14

ÃŃky

0.14

atee

0.14

rud

0.14

è¹

0.14

uler

0.14

Activations Density 0.013%

references to flashbacks or related terms in narrative contexts

No Comments

No Known Activations