INDEX

Explanations

comparative terms indicating superiority or performance, especially in a political or economic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

fal

-0.16

yclopedia

-0.16

cete

-0.15

icional

-0.14

zia

-0.14

duk

-0.14

ette

-0.14

ampo

-0.14

ÙıÙĪØ§

-0.14

ulur

-0.14

POSITIVE LOGITS

 even

0.28

even

0.22

any

0.22

 Ð´Ð°Ð¶Ðµ

0.19

 than

0.18

çĶļèĩ³

0.18

 EVEN

0.17

 ever

0.17

 anything

0.17

 mere

0.17

Activations Density 0.147%

comparative terms indicating superiority or performance, especially in a political or economic context

No Comments

No Known Activations