INDEX

Explanations

references to "pot" in various contexts, including its usage in phrases and related terms

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

ubi

-0.15

enaire

-0.15

Ã»

-0.15

HING

-0.15

arsity

-0.15

agit

-0.14

datatable

-0.14

PCA

-0.14

orning

-0.14

orden

-0.14

POSITIVE LOGITS

atoes

0.26

tery

0.26

entially

0.25

ting

0.25

assium

0.25

pour

0.24

ENTIAL

0.23

luck

0.23

enti

0.21

folio

0.20

Activations Density 0.013%

references to "pot" in various contexts, including its usage in phrases and related terms

No Comments

No Known Activations