INDEX

Explanations

mentions of specific individuals or names in a context of emotional or social events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

à¸²à¸£à¸°

-0.16

pedia

-0.16

ESA

-0.15

ETYPE

-0.14

å°¾

-0.14

 MASK

-0.14

ãĥ³ãĤ¬

-0.14

ULK

-0.14

bane

-0.13

 è»Ĭ

-0.13

POSITIVE LOGITS

 President

0.20

kle

0.19

President

0.17

 Presidential

0.17

APC

0.17

 president

0.16

 Loot

0.16

Pres

0.16

-pres

0.15

 Vice

0.15

Activations Density 0.045%

mentions of specific individuals or names in a context of emotional or social events

No Comments

No Known Activations