INDEX

Explanations

references to dialogue and dialog-related structures in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

MENT

-0.16

ment

-0.16

 slee

-0.15

bound

-0.15

ugg

-0.15

aby

-0.15

idge

-0.14

ãģŀ

-0.14

igans

-0.14

cher

-0.14

POSITIVE LOGITS

ues

0.30

/dialog

0.20

UES

0.19

uese

0.18

atical

0.16

(Dialog

0.16

gable

0.15

ãģĤãģ£ãģŁ

0.15

UE

0.15

çĽ¸æīĭ

0.15

Activations Density 0.013%

references to dialogue and dialog-related structures in text

No Comments

No Known Activations