INDEX

Explanations

references to "pin" or variations of it, indicating a focus on images or items associated with pinning or Pinterest

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

UME

-0.18

umas

-0.17

ÙİØ§

-0.15

addin

-0.15

enor

-0.15

ucht

-0.15

Separated

-0.15

zte

-0.14

umbles

-0.14

 Ø§Ø¶

-0.14

POSITIVE LOGITS

ola

0.15

ado

0.15

sec

0.15

nes

0.14

 NotImplemented

0.14

_void

0.14

ck

0.14

ìĥĿ

0.14

TP

0.14

ä¾¯

0.14

Activations Density 0.008%

references to "pin" or variations of it, indicating a focus on images or items associated with pinning or Pinterest

No Comments

No Known Activations