INDEX

Explanations

titles related to leadership and executive positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

celik

-0.16

ALCHEMY

-0.15

ÙħØ²

-0.15

czy

-0.14

iram

-0.14

 gall

-0.14

pany

-0.14

åĵ

-0.14

).__

-0.13

egen

-0.13

POSITIVE LOGITS

 responsible

0.18

/ch

0.17

åħ¼

0.15

-controller

0.15

hips

0.15

ships

0.15

inch

0.15

em

0.15

ially

0.15

/controller

0.15

Activations Density 0.020%

titles related to leadership and executive positions

No Comments

No Known Activations