INDEX

Explanations

mentions of academic titles or roles

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

ough

-0.16

istically

-0.15

Ã³t

-0.15

AZY

-0.14

moth

-0.14

orph

-0.14

edral

-0.14

Ð¾Ð¿ÑĢÐ¾Ñģ

-0.14

ucken

-0.14

POSITIVE LOGITS

ial

0.29

 Emer

0.21

ship

0.20

iate

0.19

ships

0.18

IAL

0.17

umo

0.17

ession

0.15

ess

0.15

SHIP

0.15

Activations Density 0.014%

mentions of academic titles or roles

No Comments

No Known Activations