INDEX

Explanations

occurrences of the word "start" and related phrases that suggest the initiation or beginning of an action or process

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

istrat

-0.16

URITY

-0.16

rouch

-0.15

ed

-0.15

ISE

-0.15

abin

-0.14

olson

-0.14

ospace

-0.14

ÑħÑĢÐ°Ð½

-0.14

ABB

-0.14

POSITIVE LOGITS

ups

0.25

seite

0.23

-ups

0.23

swith

0.22

-up

0.21

ovacÃŃ

0.20

upper

0.20

eg

0.20

ovnÃŃ

0.19

tls

0.19

Activations Density 0.027%

occurrences of the word "start" and related phrases that suggest the initiation or beginning of an action or process

No Comments

No Known Activations