INDEX

Explanations

punctuation and conjunctions, indicating relationships and continuities in speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

erus

-0.16

teri

-0.15

ALS

-0.15

deaux

-0.15

pedia

-0.15

\/\/

-0.14

merc

-0.14

uttle

-0.14

/Peak

-0.14

meyi

-0.14

POSITIVE LOGITS

hack

0.18

 Hack

0.14

 Bren

0.14

OND

0.14

 Metal

0.14

 hack

0.13

Od

0.13

Hack

0.13

 wart

0.13

 Bain

0.13

Activations Density 0.002%

punctuation and conjunctions, indicating relationships and continuities in speech

No Comments

No Known Activations