INDEX

Explanations

instances of the verb "read" and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

arto

-0.15

edia

-0.15

 Lindsey

-0.15

Cow

-0.15

 Lady

-0.15

quet

-0.15

ampo

-0.14

anst

-0.14

 vide

-0.14

Whe

-0.14

POSITIVE LOGITS

/watch

0.26

(æ°´

0.20

 about

0.18

ÙĦÛĮÙħ

0.16

(æľ¨

0.16

(read

0.16

ToEnd

0.16

/tags

0.15

ãĤ¿ãĥ³

0.15

 reviews

0.15

Activations Density 0.034%

instances of the verb "read" and its derivatives

No Comments

No Known Activations