INDEX

Explanations

details related to race performance and positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

istream

-0.15

olet

-0.14

NOM

-0.14

bench

-0.14

Ø´Ø¯

-0.13

lant

-0.13

 Cout

-0.13

 Bench

-0.13

bakan

-0.13

ucken

-0.13

POSITIVE LOGITS

ongyang

0.18

åľĪ

0.17

 poles

0.17

pil

0.16

quin

0.16

 driver

0.15

 stalk

0.15

lap

0.15

.gridColumn

0.15

 Charging

0.15

Activations Density 0.026%

details related to race performance and positioning

No Comments

No Known Activations