INDEX

Explanations

terms related to guarantees and obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

urve

-0.16

éĥ

-0.16

deps

-0.16

itian

-0.15

bane

-0.15

 Ð¿Ð¾Ð±Ð°

-0.14

alt

-0.14

inputEmail

-0.14

kes

-0.14

ARCH

-0.14

POSITIVE LOGITS

tres

0.17

ogne

0.16

wers

0.14

ren

0.14

ÑĢÐ¸Ð¼

0.13

à¹ģà¸Ī

0.13

ewise

0.13

inn

0.13

×ķ

0.13

Activations Density 0.010%

terms related to guarantees and obligations

No Comments

No Known Activations