INDEX

Explanations

the name "Nathan" 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

hek

-0.17

lund

-0.17

innen

-0.17

elts

-0.17

UPER

-0.17

à¸±à¸į

-0.16

æĲ¬

-0.15

holm

-0.15

Å¾it

-0.15

ELY

-0.15

POSITIVE LOGITS

ial

0.29

aniel

0.21

iele

0.19

ail

0.19

IEL

0.18

alie

0.17

ials

0.16

alysis

0.16

Activations Density 0.008%

the name "Nathan" in various contexts

No Comments

No Known Activations