INDEX

Explanations

references to various administrative or governmental levels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

/generated

-0.18

 billig

-0.15

ware

-0.14

Ð»Ð°Ð²

-0.14

 Virt

-0.14

ayet

-0.14

 ë©´

-0.14

ene

-0.14

fa

-0.14

regular

-0.14

POSITIVE LOGITS

uentes

0.17

ULER

0.16

Äįit

0.16

hart

0.16

 INTERRUPTION

0.15

ouns

0.15

harma

0.15

iant

0.15

0.14

vÄĽ

0.14

Activations Density 0.020%

references to various administrative or governmental levels

No Comments

No Known Activations