INDEX

Explanations

terms related to discounts and deals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

itar

-0.17

istically

-0.17

strict

-0.16

longleftrightarrow

-0.15

ampo

-0.15

fault

-0.15

chod

-0.15

uments

-0.15

Äįek

-0.14

enge

-0.14

POSITIVE LOGITS

enance

0.22

/free

0.21

able

0.21

ssp

0.17

ing

0.17

edList

0.16

ation

0.16

ting

0.16

ABLE

0.15

ive

0.15

Activations Density 0.012%

terms related to discounts and deals

No Comments

No Known Activations