INDEX

Explanations

instances of the word "and" as a connective

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

lobber

-0.15

lero

-0.14

adia

-0.14

ivities

-0.13

esses

-0.13

iano

-0.13

Ð³Ðµ

-0.13

ÎºÎ±Î¹

-0.13

iples

-0.13

icus

-0.13

POSITIVE LOGITS

rez

0.17

elage

0.16

eni

0.14

 ÎĳÎł

0.14

ziej

0.14

reeze

0.14

ohana

0.14

Arrow

0.14

 pParent

0.14

ÏĦÏĥ

0.14

Activations Density 0.055%

instances of the word "and" as a connective

No Comments

No Known Activations