INDEX

Explanations

actions related to trying, visiting, and experiencing activities or attractions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Miner

-0.15

isms

-0.15

/an

-0.15

 plug

-0.14

to

-0.13

/apps

-0.13

ITERAL

-0.13

":[{↵

-0.13

avy

-0.13

 colony

-0.13

POSITIVE LOGITS

/print

0.17

/remove

0.17

/use

0.16

able

0.16

ibly

0.16

erno

0.15

ono

0.14

ables

0.14

 oneself

0.14

/watch

0.14

Activations Density 0.159%

actions related to trying, visiting, and experiencing activities or attractions

No Comments

No Known Activations