INDEX

Explanations

negations and expressions of complexity in relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ied

-0.16

ãĥĶãĥ¼

-0.16

isse

-0.15

ê·¼

-0.13

hp

-0.13

jud

-0.13

imore

-0.13

okt

-0.13

ÅĻej

-0.13

Ð½Ð°Ð½Ð½Ñı

-0.13

POSITIVE LOGITS

ecom

0.19

ngrx

0.16

oga

0.15

LK

0.15

kj

0.15

uben

0.15

tak

0.14

ucket

0.14

eva

0.14

alem

0.14

Activations Density 0.137%

negations and expressions of complexity in relationships

No Comments

No Known Activations