INDEX

Explanations

addresses and location-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

okers

-0.16

egl

-0.15

laden

-0.15

 èĢ

-0.15

rana

-0.15

oksen

-0.14

anners

-0.14

ãģ¾ãģ¾

-0.14

kur

-0.14

ilan

-0.14

POSITIVE LOGITS

0.15

PAD

0.15

ãĥ³ãĤ°

0.15

iro

0.14

 Huffman

0.14

oup

0.14

 Doming

0.14

Activations Density 0.050%

addresses and location-related information

No Comments

No Known Activations