INDEX

Explanations

forms of the word "fix" and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

rial

-0.17

iler

-0.15

alu

-0.15

kol

-0.14

ought

-0.14

shan

-0.14

kir

-0.14

ajan

-0.14

AndPassword

-0.14

ILER

-0.14

POSITIVE LOGITS

tures

0.33

TURE

0.25

ated

0.22

(es

0.20

er

0.20

à¤¼

0.19

gerald

0.19

 broken

0.19

ity

0.17

xed

0.17

Activations Density 0.051%

forms of the word "fix" and related concepts

No Comments

No Known Activations