INDEX

Explanations

references to universities and institutions associated with the word "Queen."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

icont

-0.16

aye

-0.16

-0.15

Ã«n

-0.15

wen

-0.15

ivals

-0.14

ãĤĥ

-0.14

Äĩ

-0.14

plet

-0.14

POSITIVE LOGITS

Disposition

0.15

fcc

0.15

ago

0.14

$($

0.14

atoria

0.14

Anc

0.14

çīĪ

0.14

 chan

0.13

-chan

0.13

 conc

0.13

Activations Density 0.012%

references to universities and institutions associated with the word "Queen."

No Comments

No Known Activations