INDEX

Explanations

expressions of gratitude

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

 Intervention

-0.15

SSIP

-0.15

ves

-0.15

iang

-0.15

rec

-0.14

 concent

-0.14

 intervention

-0.14

ikki

-0.14

ergic

-0.14

POSITIVE LOGITS

stdClass

0.18

*)_

0.16

chwitz

0.16

warts

0.15

 Ð²ÑģÐµÐ³Ð¾

0.15

fur

0.14

ìĿ´ëĵľ

0.14

áº¡ch

0.14

è¤

0.14

_HP

0.14

Activations Density 0.013%

expressions of gratitude

No Comments

No Known Activations