INDEX

Explanations

references to scientific methodologies and data processing techniques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 absor

-0.16

 deficits

-0.14

ãİ

-0.14

porte

-0.14

\<^

-0.14

IFS

-0.14

folk

-0.13

Keywords

-0.13

ãĥ§

-0.13

 Bundy

-0.13

POSITIVE LOGITS

 cigar

0.25

 reads

0.25

bam

0.24

 Reads

0.24

 FAST

0.23

 alignments

0.23

 Illum

0.22

 fast

0.22

FAST

0.22

Bam

0.21

Activations Density 0.058%

references to scientific methodologies and data processing techniques

No Comments

No Known Activations