INDEX

Explanations

specific names and terms associated with various contexts, including sports, technology, and fictional narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

avour

-0.14

 TResult

-0.14

%(

-0.13

 enqu

-0.12

poss

-0.12

 fakat

-0.12

ìĭ¸

-0.12

Displayed

-0.11

%M

-0.11

@student

-0.11

POSITIVE LOGITS

ain

0.28

 sure

0.27

IS

0.21

 shouldn

0.20

 kind

0.20

 aside

0.19

!=

0.19

 notwithstanding

0.19

 sucks

0.19

Activations Density 0.438%

specific names and terms associated with various contexts, including sports, technology, and fictional narratives

No Comments

No Known Activations