INDEX

Explanations

references to individuals or groups of people 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ziel

-0.15

acie

-0.15

æĹ¦

-0.15

stoupil

-0.15

town

-0.14

ntl

-0.14

exo

-0.14

ener

-0.14

dÃ¼r

-0.14

uela

-0.14

POSITIVE LOGITS

kdo

0.15

ailable

0.14

azen

0.14

0.13

 msgid

0.13

who

0.13

ava

0.13

 Trick

0.13

bar

0.13

aho

0.13

Activations Density 0.213%

references to individuals or groups of people in various contexts

No Comments

No Known Activations