INDEX

Explanations

references to specific years and chronological data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

oids

-0.17

est

-0.16

oid

-0.16

way

-0.16

ille

-0.15

erman

-0.15

yte

-0.14

aven

-0.14

adden

-0.14

 congr

-0.14

POSITIVE LOGITS

-round

0.29

ning

0.22

 round

0.19

-long

0.19

nings

0.19

round

0.18

unik

0.18

-over

0.17

long

0.17

Round

0.17

Activations Density 0.026%

references to specific years and chronological data

No Comments

No Known Activations