INDEX

Explanations

instances of denial or contradiction in statements

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

oun

-0.17

/wiki

-0.15

etsk

-0.15

 contrary

-0.14

emens

-0.14

contr

-0.14

aci

-0.14

hrad

-0.14

rÃ¡

-0.13

 Contr

-0.13

POSITIVE LOGITS

 nevertheless

0.20

 nonetheless

0.17

æŃ¡

0.15

amon

0.14

 stuck

0.14

istra

0.14

 Essentially

0.14

 ÑĦÐ°ÐºÑĤ

0.14

Nevertheless

0.13

AMS

0.13

Activations Density 0.163%

instances of denial or contradiction in statements

No Comments

No Known Activations