INDEX

Explanations

words related to conditions and criteria

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

erdem

-0.16

oulos

-0.15

amilia

-0.15

orda

-0.15

imed

-0.14

 culo

-0.14

 ÏħÏĢ

-0.14

Ã¡Äį

-0.14

allah

-0.14

 pref

-0.14

POSITIVE LOGITS

 Wass

0.17

0.16

ÃŃt

0.14

PropertyDescriptor

0.13

gnore

0.13

echa

0.13

UINT

0.13

å»Ĭ

0.13

Activations Density 0.001%

words related to conditions and criteria

No Comments

No Known Activations