INDEX

Explanations

references to the term "prospect" and its variations, indicating contexts related to prospects or opportunities

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

endon

-0.19

een

-0.15

locals

-0.15

arella

-0.15

à¸¡

-0.14

emand

-0.14

Ã¦k

-0.14

pson

-0.14

ãĤ¤ãĤº

-0.14

drawer

-0.14

POSITIVE LOGITS

ively

0.27

pective

0.26

pector

0.23

pects

0.21

ors

0.18

us

0.17

 pros

0.17

acco

0.17

uses

0.16

peri

0.16

Activations Density 0.012%

references to the term "prospect" and its variations, indicating contexts related to prospects or opportunities

No Comments

No Known Activations