INDEX

Explanations

technical terminology related to programming and software tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

çķ

-0.16

ç¥

-0.15

æ®Ĭ

-0.14

ects

-0.14

vex

-0.14

ä¸ĺ

-0.14

<&

-0.14

 religion

-0.13

ruba

-0.13

mog

-0.13

POSITIVE LOGITS

igor

0.15

ERCHANT

0.15

lico

0.14

Spe

0.14

à¸ªà¸Ļ

0.14

EOF

0.14

 Bers

0.13

Spe

0.13

æħİ

0.13

Deal

0.13

Activations Density 0.008%

technical terminology related to programming and software tools

No Comments

No Known Activations