INDEX

Explanations

programming-related terms and concepts

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

cala

-0.18

 Permanent

-0.17

ÑĩÐ¸Ð½Ð¸

-0.17

olio

-0.15

anus

-0.15

/respond

-0.15

Permanent

-0.15

ãĤ¿ãĥ«

-0.14

 Ð±Ð°Ð³

-0.14

 permanent

-0.14

POSITIVE LOGITS

 operator

0.47

operator

0.41

-operator

0.35

 operators

0.35

 Operator

0.33

	operator

0.29

.operator

0.29

 Operators

0.29

_operator

0.28

/operator

0.26

Activations Density 0.022%

programming-related terms and concepts

No Comments

No Known Activations