INDEX

Explanations

references to the name "Marilyn."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

estre

-0.15

ÑĭÑĤ

-0.15

otal

-0.15

emm

-0.15

kad

-0.15

emade

-0.14

ogue

-0.14

istrar

-0.13

eve

-0.13

gett

-0.13

POSITIVE LOGITS

tright

0.18

ldr

0.16

rug

0.16

 ØªØ³

0.15

alez

0.15

åĵ²

0.15

imas

0.15

Insensitive

0.15

iciar

0.14

_KHR

0.14

Activations Density 0.008%

references to the name "Marilyn."

No Comments

No Known Activations