INDEX

Explanations

military ranks and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ERSHEY

-0.14

iers

-0.14

iesz

-0.14

Threads

-0.13

å¸«

-0.13

SES

-0.13

ØŃÙĤ

-0.13

ilogy

-0.13

genes

-0.13

Ã´ng

-0.13

POSITIVE LOGITS

arrant

0.17

 Garn

0.16

 fore

0.15

 Batt

0.14

 Fore

0.14

 Inspir

0.14

 Favorite

0.14

-feedback

0.14

Eng

0.13

(named

0.13

Activations Density 0.141%

military ranks and titles

No Comments

No Known Activations