INDEX

Explanations

references to historical concepts or events

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

omm

-0.16

tha

-0.15

onom

-0.14

Dies

-0.14

ERP

-0.13

irÃ¡

-0.13

sum

-0.13

antium

-0.13

 Baker

-0.13

Ð¾ÑĢÐ°Ð·

-0.13

POSITIVE LOGITS

 trace

0.34

 earliest

0.33

trace

0.30

 traces

0.30

 traced

0.30

 history

0.28

 first

0.28

 began

0.28

istory

0.26

history

0.26

Activations Density 0.161%

references to historical concepts or events

No Comments

No Known Activations