INDEX

Explanations

references to video or multimedia content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

*sp

-0.16

elman

-0.16

ocht

-0.15

Ð°ÐºÐ¾Ð²

-0.15

ValuePair

-0.15

ÑıÐ´

-0.15

ikan

-0.15

igth

-0.14

NavItem

-0.14

krv

-0.14

POSITIVE LOGITS

 Spears

0.16

 happened

0.15

ita

0.15

oma

0.15

cas

0.15

ma

0.15

ano

0.14

et

0.14

ereg

0.14

Activations Density 0.012%

references to video or multimedia content

No Comments

No Known Activations