INDEX

Explanations

references to captains in various contexts

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

las

-0.17

utom

-0.16

 setFrame

-0.15

REN

-0.14

 precious

-0.14

IDDEN

-0.14

away

-0.14

ites

-0.14

Las

-0.14

POSITIVE LOGITS

eut

0.15

strup

0.15

resco

0.14

erture

0.14

 calling

0.14

agne

0.14

Ð¾Ð½ÑĮ

0.14

Ð¾Ð²Ð°ÑĢ

0.14

anners

0.14

Ã¡Å¾e

0.14

Activations Density 0.010%

references to captains in various contexts

No Comments

No Known Activations