INDEX

Explanations

terms and phrases related to technical or programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Cust

-0.15

Ost

-0.14

 aure

-0.13

ssue

-0.13

EXPECTED

-0.13

Ø§ÙĦÙĬ

-0.13

Helpers

-0.13

 Threat

-0.13

ffa

-0.13

POSITIVE LOGITS

eshire

0.16

eca

0.15

egl

0.15

iferay

0.15

engkap

0.15

COPE

0.15

 Transparency

0.14

herits

0.14

ande

0.14

oker

0.14

Activations Density 0.775%

terms and phrases related to technical or programming concepts

No Comments

No Known Activations