INDEX

Explanations

phrases related to progress and continuity in actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ret

-0.17

ling

-0.17

ados

-0.16

stab

-0.16

ita

-0.15

rap

-0.15

aph

-0.15

lop

-0.15

ilip

-0.14

lings

-0.14

POSITIVE LOGITS

ä¸ĭåİ»

0.21

noinspection

0.16

otel

0.15

 dÃ¡le

0.15

icerca

0.15

 addCriterion

0.14

ìĸ´ìĦľ

0.14

Î¹ÏĥÎµ

0.14

Hang

0.14

Activations Density 0.059%

phrases related to progress and continuity in actions or processes

No Comments

No Known Activations