INDEX

Explanations

references to "pin" in various contexts, particularly related to the social media platform Pinterest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

edor

-0.19

ummies

-0.15

ÅĻil

-0.15

stown

-0.15

/display

-0.15

inges

-0.15

eÅŁit

-0.15

Ã¤tz

-0.14

ë·

-0.14

owitz

-0.14

POSITIVE LOGITS

ning

0.35

Pin

0.20

ners

0.19

ny

0.19

heiro

0.19

NING

0.19

Pin

0.19

lerce

0.18

.Pin

0.18

ching

0.17

Activations Density 0.018%

references to "pin" in various contexts, particularly related to the social media platform Pinterest

No Comments

No Known Activations