INDEX

Explanations

various formulations of the word "approach."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

vez

-0.17

ized

-0.16

UTE

-0.16

uti

-0.15

ute

-0.15

ãĤĴãģ¤

-0.15

enties

-0.15

à¸¡

-0.15

 Harden

-0.15

ansi

-0.14

POSITIVE LOGITS

(es

0.29

able

0.28

erif

0.19

esch

0.16

 tslint

0.15

esto

0.15

getDb

0.15

ability

0.15

esa

0.15

inski

0.15

Activations Density 0.022%

various formulations of the word "approach."

No Comments

No Known Activations