INDEX

Explanations

instances of self-contradiction and arguments about morality and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

erp

-0.16

 Morales

-0.16

ermen

-0.16

sov

-0.16

dle

-0.15

IRT

-0.15

 expend

-0.14

ÐµÑĢÐ¿

-0.14

ç´

-0.14

loe

-0.14

POSITIVE LOGITS

gfx

0.15

opia

0.14

ano

0.14

clip

0.14

 Alic

0.14

Pl

0.14

 Escape

0.14

Tu

0.14

Escape

0.14

amel

0.14

Activations Density 0.422%

instances of self-contradiction and arguments about morality and values

No Comments

No Known Activations