INDEX

Explanations

mentions of modifications or changes in processes or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

.raises

-0.15

ÑİÐº

-0.15

avax

-0.15

ADX

-0.15

-0.14

 sidelines

-0.14

airo

-0.14

rists

-0.14

aira

-0.14

 Naked

-0.14

POSITIVE LOGITS

onse

0.15

 togg

0.15

.chapter

0.15

 kali

0.15

ä»ĭ

0.14

 collusion

0.14

Lep

0.14

ãĤ¿ãĥ«

0.14

ton

0.14

 mund

0.14

Activations Density 0.016%

mentions of modifications or changes in processes or systems

No Comments

No Known Activations