INDEX

Explanations

phrases indicating moral or ethical considerations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.14

shi

-0.14

ÅĽnie

-0.14

raig

-0.14

.rf

-0.14

rr

-0.13

ASA

-0.13

gart

-0.13

ls

-0.13

POSITIVE LOGITS

puted

0.17

celed

0.17

emachine

0.15

impse

0.15

imson

0.15

ToEnd

0.15

deaux

0.14

ãĥ«ãĥī

0.14

utzer

0.14

.Plugin

0.14

Activations Density 0.756%

phrases indicating moral or ethical considerations

No Comments

No Known Activations