INDEX

Explanations

phrases related to personal achievements and skills

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

 eskort

-0.13

áº¯c

-0.13

avian

-0.13

á»ĳc

-0.12

ughter

-0.12

ISCO

-0.11

.DataVisualization

-0.11

Ð¸Ð¼Ðµ

-0.11

.updateDynamic

-0.11

Â³

-0.11

POSITIVE LOGITS

 Uncategorized

0.14

 famously

0.13

fwd

0.13

 incentiv

0.12

 probs

0.11

Åº

0.11

 crazy

0.11

bout

0.11

 lots

0.11

 incl

0.11

Activations Density 0.152%

phrases related to personal achievements and skills

No Comments

No Known Activations