INDEX

Explanations

elements related to programming and data structures

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

á»§ng

-0.14

 norge

-0.14

.fromFunction

-0.13

 RegexOptions

-0.13

 addCriterion

-0.13

EXPR

-0.13

Ð·Ð½Ð°ÑĩÐ°

-0.13

decorators

-0.12

"group

-0.12

_consts

-0.12

POSITIVE LOGITS

Âł

0.18

âĢ¦↵

0.18

âĢ¦

0.17

 âĢ¦

0.15

 âĢ¦↵

0.15

 [âĢ¦]↵

0.14

 [âĢ¦]

0.13

âĢ¦”

0.13

“

0.13

 Â«

0.12

Activations Density 1.719%

elements related to programming and data structures

No Comments

No Known Activations