INDEX

Explanations

mathematical notation and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

oris

-0.15

adu

-0.15

ernaut

-0.14

ile

-0.14

 Î¼ÎŃ

-0.14

 Mountain

-0.14

oran

-0.14

Sortable

-0.14

åĲĽ

-0.13

POSITIVE LOGITS

 RedirectTo

0.15

nh

0.15

ToWorld

0.14

ÏĦÏį

0.14

oons

0.14

 sniper

0.14

ulse

0.14

umno

0.14

 pits

0.14

 --------------------------------------------------------------------------↵

0.13

Activations Density 0.087%

mathematical notation and formatting

No Comments

No Known Activations