INDEX

Explanations

specific technical terms and terminology related to programming and technology developments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ãĥĥãĥĦ

-0.18

lify

-0.16

.dp

-0.15

_EOF

-0.14

elves

-0.14

atte

-0.14

rans

-0.14

empor

-0.14

lef

-0.14

/Gate

-0.14

POSITIVE LOGITS

annah

0.16

HEME

0.15

 Wein

0.14

Sau

0.14

Dil

0.14

 artificial

0.14

é¬¼

0.14

Pek

0.14

Ã¡nh

0.14

Activations Density 0.012%

specific technical terms and terminology related to programming and technology developments

No Comments

No Known Activations