INDEX

Explanations

references to the act of "pinning" content, particularly related to Pinterest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ummies

-0.16

łģ

-0.16

Ð°Ð»Ð¾Ð¼

-0.15

 inval

-0.15

_pemb

-0.14

Ð°Ð»Ðµ

-0.14

encer

-0.14

tring

-0.14

udder

-0.14

-0.13

POSITIVE LOGITS

pin

0.18

-pin

0.18

points

0.17

ning

0.17

Pin

0.17

 pinned

0.17

 pins

0.16

Pin

0.16

pin

0.16

.pin

0.16

Activations Density 0.020%

references to the act of "pinning" content, particularly related to Pinterest

No Comments

No Known Activations