INDEX

Explanations

the term "so" used for emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.16

antry

-0.16

ammo

-0.15

Resolution

-0.14

dig

-0.14

Alv

-0.14

Criterion

-0.14

astle

-0.14

Indices

-0.14

NSK

-0.13

POSITIVE LOGITS

aring

0.31

-called

0.27

ho

0.26

jour

0.26

apy

0.25

aking

0.25

Cal

0.25

zial

0.24

Ho

0.24

aps

0.23

Activations Density 0.024%

the term "so" used for emphasis

No Comments

No Known Activations