INDEX

Explanations

phrases expressing conclusions or ultimate outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

akk

-0.15

æ¿

-0.15

 already

-0.15

uch

-0.14

Re

-0.14

rol

-0.14

 Gerr

-0.14

/tag

-0.13

chaft

-0.13

 Clear

-0.13

POSITIVE LOGITS

 ultimately

0.22

 Ultimately

0.20

 eventual

0.18

Ultimately

0.17

 Eventually

0.16

 eventually

0.16

 nakonec

0.15

MOST

0.15

pline

0.15

ertz

0.15

Activations Density 0.057%

phrases expressing conclusions or ultimate outcomes

No Comments

No Known Activations