INDEX

Explanations

instances of representation in discussions or contexts related to organizations, committees, or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ani

-0.15

town

-0.15

aret

-0.15

asco

-0.15

ari

-0.15

taj

-0.14

perator

-0.14

eno

-0.14

aza

-0.14

ara

-0.14

POSITIVE LOGITS

aint

0.18

enville

0.17

ãĥ£

0.16

adb

0.15

Ð¾ÑĢÑĤ

0.14

ever

0.14

Å¡el

0.14

orgen

0.14

":-

0.13

\application

0.13

Activations Density 0.025%

instances of representation in discussions or contexts related to organizations, committees, or groups

No Comments

No Known Activations