INDEX

Explanations

specific or formal names and titles related to individuals in professional contexts

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

 investigations

-0.14

 yearly

-0.14

thag

-0.14

 utilizing

-0.13

Util

-0.13

 Investigations

-0.13

ansa

-0.13

erten

-0.13

phet

-0.13

...

-0.13

POSITIVE LOGITS

 âĢ¦.

0.20

 sector

0.17

sector

0.17

âĢ¦..

0.16

 resil

0.16

âĢ¦âĢ¦

0.16

 Sector

0.16

-sector

0.15

 CEOs

0.15

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

0.15

Activations Density 0.003%

specific or formal names and titles related to individuals in professional contexts

No Comments

No Known Activations