INDEX

Explanations

titles and roles associated with leadership positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ayer

-0.16

Ã¨ve

-0.15

EventHandler

-0.15

}elseif

-0.14

Ã´m

-0.14

 erotisch

-0.14

ograd

-0.14

okers

-0.14

 å®

-0.14

AsString

-0.14

POSITIVE LOGITS

setOnClickListener

0.16

quette

0.15

TED

0.14

 Leban

0.13

ouis

0.13

 elsewhere

0.13

 pant

0.13

.bed

0.13

ementia

0.13

Activations Density 0.067%

titles and roles associated with leadership positions

No Comments

No Known Activations