INDEX

Explanations

words related to personalized or custom products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 leather

-0.15

 Sculpt

-0.15

 Leather

-0.14

ozem

-0.14

 jewellery

-0.14

 blonde

-0.14

aylight

-0.14

 blond

-0.14

 Heap

-0.13

 Blonde

-0.13

POSITIVE LOGITS

 patterns

0.33

 pattern

0.32

-pattern

0.29

patterns

0.29

pattern

0.28

 Patterns

0.28

.pattern

0.28

 Pattern

0.28

_pattern

0.27

Pattern

0.26

Activations Density 0.104%

words related to personalized or custom products

No Comments

No Known Activations