INDEX

Explanations

questions or prompts that indicate a request for information or assessment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

SizePolicy

-0.15

ever

-0.14

.persist

-0.14

eÄį

-0.13

plorer

-0.13

eca

-0.13

 separ

-0.13

ici

-0.13

ica

-0.13

 preds

-0.13

POSITIVE LOGITS

ocator

0.17

 Blasio

0.15

ÐµÐ½Ð´

0.14

 Sesso

0.14

å§Ķåĳĺä¼ļ

0.14

 GenerationType

0.13

cil

0.13

inges

0.13

ï¼ī:

0.13

Activations Density 6.421%

questions or prompts that indicate a request for information or assessment

No Comments

No Known Activations