INDEX

Explanations

instances of comparisons or qualifiers regarding expectations and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ã¡o

-0.15

arium

-0.15

 latina

-0.15

ï¼Ĩ

-0.13

.wp

-0.13

variants

-0.13

 McCarthy

-0.12

 à¤ķà¤Ī

-0.12

 Latina

-0.12

ominator

-0.12

POSITIVE LOGITS

how

0.21

 finances

0.21

timing

0.17

 timing

0.17

 politics

0.17

 whether

0.17

0.16

how

0.16

 myself

0.16

 matters

0.15

Activations Density 0.299%

instances of comparisons or qualifiers regarding expectations and relationships

No Comments

No Known Activations