INDEX

Explanations

instructions related to scrolling actions and behaviors in user interfaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ekil

-0.18

ernals

-0.16

assen

-0.15

ikan

-0.15

cken

-0.14

ymbols

-0.14

rist

-0.14

ovice

-0.14

jal

-0.14

lify

-0.14

POSITIVE LOGITS

able

0.21

ingly

0.17

Ļæ±Ł

0.16

-roll

0.16

tape

0.16

 naked

0.15

ottom

0.14

Î³Î¹

0.14

 tape

0.14

-spin

0.14

Activations Density 0.019%

instructions related to scrolling actions and behaviors in user interfaces

No Comments

No Known Activations