INDEX

Explanations

phrases that suggest high levels of emotional or situational intensity

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

/plain

-0.18

oret

-0.17

à¥ĩà¤ľ

-0.17

orem

-0.17

lÄ±ÄŁÄ±nÄ±

-0.15

ias

-0.15

ÑŁ

-0.14

jug

-0.14

rias

-0.14

ester

-0.14

POSITIVE LOGITS

dek

0.18

 exclusively

0.16

_NOTICE

0.15

 MÃ©d

0.15

agt

0.14

arendra

0.14

âĢĮÙħ

0.14

.mybatisplus

0.13

ostÃŃ

0.13

mary

0.13

Activations Density 0.092%

phrases that suggest high levels of emotional or situational intensity

No Comments

No Known Activations