INDEX

Explanations

instances of the word "learn" in context

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

 Bare

-0.15

butt

-0.15

 Fashion

-0.15

 fashion

-0.14

å¸¯

-0.14

oul

-0.14

DUCT

-0.14

acias

-0.13

iona

-0.13

 bare

-0.13

POSITIVE LOGITS

rock

0.15

 marty

0.15

enin

0.15

åĲ¦

0.14

malÄ±

0.14

hma

0.14

elling

0.13

 pisc

0.13

hra

0.13

ØµØŃ

0.13

Activations Density 0.021%

instances of the word "learn" in context

No Comments

No Known Activations