INDEX

Explanations

references to programming classes and structures in code

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

.mime

-0.14

 Wake

-0.14

reten

-0.14

 Impress

-0.13

 é¤

-0.13

VIRTUAL

-0.13

Ð¼Ð¸ÑĢ

-0.13

andr

-0.13

orts

-0.13

 Smile

-0.13

POSITIVE LOGITS

STYPE

0.16

ennes

0.16

jak

0.15

ousand

0.15

ivate

0.15

icari

0.14

 ÐĽÑĮÐ²

0.14

urai

0.14

raman

0.14

eward

0.13

Activations Density 0.036%

references to programming classes and structures in code

No Comments

No Known Activations