INDEX

Explanations

references to significant moments or instances in time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

combe

-0.16

bone

-0.16

hold

-0.16

essler

-0.16

abet

-0.16

innen

-0.15

head

-0.15

isse

-0.15

holm

-0.15

chant

-0.14

POSITIVE LOGITS

aneous

0.36

ous

0.34

arily

0.34

ary

0.34

aneously

0.32

ously

0.26

ARY

0.23

ums

0.23

OUS

0.22

eous

0.22

Activations Density 0.027%

references to significant moments or instances in time

No Comments

No Known Activations

references to significant moments or instances in time

No Comments

No Known Activations