INDEX

Explanations

references to foreign entities or international contexts

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

apor

-0.16

endencies

-0.15

lobal

-0.15

infeld

-0.15

Zuk

-0.14

phan

-0.14

RIORITY

-0.14

insk

-0.14

phans

-0.14

loid

-0.14

POSITIVE LOGITS

/local

0.18

à¯įà®

0.15

iability

0.14

adal

0.14

CED

0.14

 pres

0.14

Marsh

0.14

Lens

0.14

lander

0.14

vise

0.14

Activations Density 0.024%

references to foreign entities or international contexts

No Comments

No Known Activations