INDEX

Explanations

terminology related to unpredictability and obstacles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

iek

-0.17

uche

-0.16

 Walton

-0.15

uct

-0.15

Ã³i

-0.15

alian

-0.14

 Spicer

-0.14

ī

-0.14

Ì

-0.14

 getField

-0.14

POSITIVE LOGITS

 Kore

0.20

ugi

0.16

ided

0.16

ÑĨÑĥ

0.15

 hall

0.14

arem

0.14

anga

0.14

shaw

0.14

oons

0.14

 guards

0.14

Activations Density 0.022%

terminology related to unpredictability and obstacles

No Comments

No Known Activations