INDEX

Explanations

items related to safety and operational efficiency in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

cep

-0.14

enez

-0.14

çī

-0.14

aret

-0.14

aur

-0.14

aise

-0.14

alley

-0.14

lus

-0.13

VERR

-0.13

POSITIVE LOGITS

 whose

0.17

 destiny

0.16

ibri

0.15

oom

0.15

 Destiny

0.15

ibu

0.15

ablish

0.14

fc

0.14

 perspective

0.14

whose

0.14

Activations Density 0.432%

items related to safety and operational efficiency in various contexts

No Comments

No Known Activations