INDEX

Explanations

instances of the word "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

odable

-0.17

olina

-0.17

orman

-0.15

istol

-0.15

ily

-0.15

èĲ½

-0.15

Ð¬

-0.15

aban

-0.14

ched

-0.14

POSITIVE LOGITS

 Circle

0.16

ovich

0.15

0.14

arrant

0.14

 circle

0.14

sor

0.14

cipher

0.14

Î»Î¼

0.14

-packages

0.14

icens

0.13

Activations Density 0.144%

instances of the word "in."

No Comments

No Known Activations