INDEX

Explanations

programming concepts related to object-oriented programming and module systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

oby

-0.14

AutoSize

-0.14

.Logf

-0.13

 Daha

-0.13

Ã¤t

-0.13

éĶĭ

-0.13

eps

-0.13

Mor

-0.13

 More

-0.13

 Proud

-0.13

POSITIVE LOGITS

ellipsis

0.16

__č↵

0.15

__,↵

0.15

ãĥªãĤ«

0.15

edla

0.14

inker

0.14

__/

0.14

__((

0.14

__(

0.14

ÏĦÏİ

0.14

Activations Density 0.012%

programming concepts related to object-oriented programming and module systems

No Comments

No Known Activations