INDEX

Explanations

the name "Jessica" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

elda

-0.17

boru

-0.15

OwnProperty

-0.15

¦y

-0.14

andle

-0.14

ylv

-0.14

incident

-0.14

jid

-0.14

oft

-0.14

idential

-0.14

POSITIVE LOGITS

igkeit

0.18

enet

0.16

odor

0.15

Ñİ

0.15

hawk

0.14

ws

0.13

/group

0.13

Hub

0.13

notated

0.13

Activations Density 0.002%

the name "Jessica" in various contexts

No Comments

No Known Activations