INDEX

Explanations

symbols and formatting used in legal documents or texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

rai

-0.16

tra

-0.15

ales

-0.14

atis

-0.14

riere

-0.13

pent

-0.13

 entertain

-0.13

Ã¡m

-0.13

hong

-0.12

ective

-0.12

POSITIVE LOGITS

 GURL

0.16

arel

0.14

estre

0.14

 Seks

0.14

koli

0.14

Bulk

0.14

Paz

0.13

 rowspan

0.13

ichick

0.13

romÄĽ

0.13

Activations Density 0.062%

symbols and formatting used in legal documents or texts

No Comments

No Known Activations