INDEX

Explanations

occurrences of the word "stretch" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

aries

-0.18

sein

-0.17

LOUR

-0.16

atak

-0.15

cert

-0.14

atr

-0.14

erah

-0.14

LOT

-0.14

kg

-0.14

oling

-0.14

POSITIVE LOGITS

/stretch

0.28

ToFit

0.22

 Stretch

0.22

stretch

0.22

 stretched

0.21

 stretch

0.21

Stretch

0.20

 stretches

0.19

 stretching

0.19

(es

0.17

Activations Density 0.011%

occurrences of the word "stretch" and its variations

No Comments

No Known Activations