INDEX

Explanations

academic affiliations and educational institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

akah

-0.17

pha

-0.17

 ValidationResult

-0.15

olik

-0.15

iag

-0.14

ĮĢ

-0.14

ni

-0.14

Contours

-0.14

aran

-0.14

 Reynolds

-0.14

POSITIVE LOGITS

Tub

0.20

 Cambridge

0.20

Tue

0.20

 Pennsylvania

0.18

pps

0.18

 Princeton

0.18

Erl

0.18

 California

0.18

 Illinois

0.17

 Oxford

0.17

Activations Density 0.055%

academic affiliations and educational institutions

No Comments

No Known Activations