INDEX

Explanations

references to leadership positions or roles

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

auen

-0.15

pend

-0.15

arrera

-0.14

amt

-0.14

orf

-0.14

duk

-0.14

Parms

-0.13

ideas

-0.13

mini

-0.13

TokenType

-0.13

POSITIVE LOGITS

ÑģÑĤÐ¸ÐºÐ°

0.16

lining

0.15

/head

0.15

lined

0.14

strong

0.14

(%)

0.14

ÑĢÐ°Ð¶

0.14

 Billing

0.13

onso

0.13

urga

0.13

Activations Density 0.013%

references to leadership positions or roles

No Comments

No Known Activations