INDEX

Explanations

instances of apologies and associated statements regarding responsibility and allegations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 serm

-0.17

adle

-0.15

uhn

-0.15

 Ledger

-0.14

ê³¤

-0.14

ophy

-0.14

eck

-0.14

enstein

-0.14

Æ¡i

-0.14

ayi

-0.14

POSITIVE LOGITS

 tender

0.18

 demand

0.18

 prima

0.17

 allegedly

0.17

 vide

0.16

 chall

0.16

demand

0.16

-demand

0.15

 copp

0.15

 tend

0.15

Activations Density 0.075%

instances of apologies and associated statements regarding responsibility and allegations

No Comments

No Known Activations