INDEX

Explanations

descriptions of emotions and personalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Ð°Ð±Ð¾

-0.15

nas

-0.15

vet

-0.14

 âĵĺ

-0.14

æ³ķ

-0.14

éĨ

-0.14

Ð²ÑģÑı

-0.13

 Willis

-0.13

ticker

-0.13

lection

-0.13

POSITIVE LOGITS

enne

0.16

iaux

0.15

kt

0.15

gra

0.14

anka

0.14

brick

0.14

essen

0.14

igm

0.13

_regularizer

0.13

 Hava

0.13

Activations Density 0.495%

descriptions of emotions and personalities

No Comments

No Known Activations