INDEX

Explanations

words associated with authority and social hierarchy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Mour

-0.15

lil

-0.15

íĿ

-0.15

ichte

-0.15

strom

-0.14

iph

-0.14

 Huffman

-0.14

pol

-0.14

.jquery

-0.14

late

-0.13

POSITIVE LOGITS

ÐµÑģÐ°

0.16

ierge

0.15

erdale

0.14

brids

0.14

isti

0.14

ersh

0.14

isper

0.14

immers

0.14

ssi

0.14

UGIN

0.14

Activations Density 0.002%

words associated with authority and social hierarchy

No Comments

No Known Activations