INDEX

Explanations

terms related to traffic lanes and road measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

åłĤ

-0.17

Ã¸r

-0.16

ildo

-0.15

kle

-0.14

ingers

-0.14

afone

-0.14

issional

-0.14

ï¿

-0.13

è¿

-0.13

IPLE

-0.13

POSITIVE LOGITS

Lar

0.17

tps

0.17

nict

0.16

0.15

anna

0.15

ForResult

0.15

licity

0.15

ĳ

0.14

etration

0.14

 Universe

0.14

Activations Density 0.008%

terms related to traffic lanes and road measurements

No Comments

No Known Activations