INDEX

Explanations

expressions related to feelings of surprise or concern

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

anik

-0.14

.newBuilder

-0.14

ellow

-0.14

utton

-0.14

è¶³

-0.14

illet

-0.14

ë¡±

-0.14

pkt

-0.13

 dokonce

-0.13

pk

-0.13

POSITIVE LOGITS

 therefore

0.18

 conclusion

0.16

ulum

0.15

 wiÄĻc

0.15

 Naturally

0.15

ewe

0.15

_UNS

0.15

cona

0.15

aten

0.14

Conclusion

0.14

Activations Density 0.072%

expressions related to feelings of surprise or concern

No Comments

No Known Activations