INDEX

Explanations

references to significant political figures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

LBL

-0.17

rip

-0.14

ovie

-0.14

è¦

-0.14

æ´¥

-0.14

ystems

-0.14

åĿĽ

-0.14

tub

-0.14

Ø¬Ùħ

-0.14

eni

-0.13

POSITIVE LOGITS

egl

0.16

izza

0.15

ÑĤÑĢÐ¾

0.15

ceso

0.14

uzzi

0.14

agma

0.14

trie

0.14

 Germ

0.14

ciz

0.13

Activations Density 0.022%

references to significant political figures and events

No Comments

No Known Activations