INDEX

Explanations

instances of negation or terms that suggest uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Jennings

-0.15

anas

-0.14

isse

-0.14

 grin

-0.14

anna

-0.14

 ============================================================================↵

-0.14

 vacuum

-0.14

 thought

-0.14

ool

-0.14

Nes

-0.14

POSITIVE LOGITS

alama

0.16

ipse

0.15

esign

0.15

imei

0.14

akk

0.14

.Stdout

0.14

 selectedIndex

0.14

IME

0.14

ahan

0.14

ehr

0.14

Activations Density 0.003%

instances of negation or terms that suggest uncertainty

No Comments

No Known Activations