INDEX

Explanations

phrases and words that indicate familial or relational connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ittal

-0.15

é¢Ĩ

-0.14

äººçļĦ

-0.14

ESCO

-0.13

ixo

-0.13

ertas

-0.13

Animating

-0.13

ersive

-0.13

ÙĪØ§Øª

-0.13

ppl

-0.13

POSITIVE LOGITS

 ranks

0.31

 crew

0.27

 team

0.26

 workforce

0.26

 audience

0.25

 group

0.25

 crowd

0.24

crew

0.23

 circle

0.22

 crews

0.22

Activations Density 0.186%

phrases and words that indicate familial or relational connections

No Comments

No Known Activations