INDEX

Explanations

the letter 'E' 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ÏĨÎ±

-0.15

 fucked

-0.14

 Harm

-0.14

ä¿ºãģ¯

-0.14

 Initi

-0.14

bol

-0.14

lem

-0.14

eph

-0.13

éĳ

-0.13

ogy

-0.13

POSITIVE LOGITS

 poorest

0.16

mapping

0.16

 Mapping

0.16

UnitTest

0.16

bang

0.15

 Economist

0.15

eg

0.15

 Belt

0.15

AI

0.15

iego

0.15

Activations Density 0.000%

the letter 'E' in various contexts

No Comments

No Known Activations