INDEX

Explanations

complex terms and phrases related to structures, methodologies, and formulations 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 @ 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

éĤ¦

-0.14

anz

-0.14

ursor

-0.14

 authorities

-0.14

 invent

-0.13

ahr

-0.13

boru

-0.13

inent

-0.13

oust

-0.13

loy

-0.13

POSITIVE LOGITS

removeAttr

0.19

0.15

0.14

emic

0.14

elder

0.14

utt

0.14

į°

0.14

icorn

0.14

Activations Density 0.015%

complex terms and phrases related to structures, methodologies, and formulations in various contexts

No Comments

No Known Activations