INDEX

Explanations

references to specific years and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

omb

-0.17

 ì·¨

-0.15

atan

-0.15

andon

-0.14

mony

-0.14

ãĤĩãģĨ

-0.14

 odpowied

-0.13

eryl

-0.13

Nos

-0.13

æ

-0.13

POSITIVE LOGITS

 year

0.19

decade

0.17

 century

0.17

istance

0.15

DDevice

0.15

 aÃ±o

0.14

year

0.14

ipi

0.14

ENDOR

0.14

ningar

0.14

Activations Density 0.104%

references to specific years and dates

No Comments

No Known Activations