INDEX

Explanations

numerical values and timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

rah

-0.16

ÃĹ↵↵

-0.16

ÑĤÐ°Ð¶

-0.16

BOTTOM

-0.15

ãĥĹãĥ©

-0.15

ottom

-0.14

mith

-0.14

pson

-0.14

Ð¼ÐµÑī

-0.14

lluminate

-0.14

POSITIVE LOGITS

ery

0.15

emann

0.15

 droit

0.14

dev

0.14

 ÅĽ

0.14

Pub

0.14

zee

0.14

ony

0.13

Hi

0.13

Activations Density 0.157%

numerical values and timestamps

No Comments

No Known Activations