INDEX

Explanations

instances of the word "closing" and related terms that indicate finality or conclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

lek

-0.16

AMIL

-0.15

abus

-0.15

ql

-0.15

ampo

-0.14

 Nack

-0.14

olini

-0.13

ulp

-0.13

bjerg

-0.13

bol

-0.13

POSITIVE LOGITS

ey

0.16

izzer

0.15

eyh

0.14

oyer

0.14

ighter

0.14

STALL

0.14

auer

0.14

jack

0.14

IPS

0.14

estination

0.13

Activations Density 0.004%

instances of the word "closing" and related terms that indicate finality or conclusion

No Comments

No Known Activations