INDEX

Explanations

references to role models and mentorship in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ø§ØªÙĩ

-0.16

ovich

-0.16

 outputs

-0.15

outputs

-0.14

elp

-0.14

dl

-0.14

pek

-0.14

 Administration

-0.14

letal

-0.14

.forName

-0.14

POSITIVE LOGITS

 Stuart

0.16

 Richards

0.16

alus

0.15

Ĺ

0.14

ernen

0.14

role

0.14

 perfect

0.14

.loadData

0.14

esan

0.14

fit

0.14

Activations Density 0.039%

references to role models and mentorship in various contexts

No Comments

No Known Activations