INDEX

Explanations

words referring to categories or classifications of objects or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

âĢĮÙĨ

-0.15

ynn

-0.15

Ì§

-0.14

ancock

-0.14

Callbacks

-0.14

AndWait

-0.14

enton

-0.14

 nakne

-0.14

-li

-0.14

unami

-0.14

POSITIVE LOGITS

/forms

0.20

(s

0.16

/type

0.16

/types

0.16

/form

0.16

/categories

0.16

ç«ĭ

0.15

/styles

0.15

/style

0.15

 Maver

0.15

Activations Density 0.037%

words referring to categories or classifications of objects or concepts

No Comments

No Known Activations