INDEX

Explanations

phrases indicating high prices or costs associated with products and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

opy

-0.17

ear

-0.15

tem

-0.15

 Companion

-0.15

der

-0.14

 assim

-0.14

 earlier

-0.14

den

-0.14

↵

-0.14

POSITIVE LOGITS

èī

0.18

edList

0.17

ataires

0.17

edata

0.17

META

0.16

rlen

0.16

ÑĢÐµÐ±

0.16

prices

0.15

 nÃ¡klad

0.15

umph

0.15

Activations Density 0.177%

phrases indicating high prices or costs associated with products and services

No Comments

No Known Activations