INDEX

Explanations

references to months and time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

enville

-0.15

spiracy

-0.15

tre

-0.14

ledon

-0.14

rist

-0.14

Silver

-0.14

 Silver

-0.14

Ð°Ð²Ð¸Ñģ

-0.13

FieldValue

-0.13

POSITIVE LOGITS

igin

0.17

tero

0.16

 fitte

0.15

Ã§on

0.15

Subsystem

0.15

Î»Î¹Î¬

0.14

erer

0.14

OMPI

0.14

athom

0.14

Ã¼t

0.14

Activations Density 0.018%

references to months and time periods

No Comments

No Known Activations