INDEX

Explanations

references to "boxes" or "containers."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

æ³¥

-0.17

ottie

-0.16

Abs

-0.16

Abs

-0.16

Ã¤r

-0.15

.Abs

-0.15

Lod

-0.15

-0.14

zell

-0.14

lauf

-0.14

POSITIVE LOGITS

ativity

0.16

fy

0.16

bay

0.15

rium

0.15

0.14

tes

0.14

Od

0.14

ç¾Ĭ

0.14

 Squadron

0.14

-back

0.13

Activations Density 0.006%

references to "boxes" or "containers."

No Comments

No Known Activations