INDEX

Explanations

numerical data and statistics related to health and economics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

atz

-0.17

 Glas

-0.16

orden

-0.15

-sem

-0.15

avier

-0.15

PI

-0.14

quette

-0.14

rew

-0.14

ÅĻeb

-0.14

tc

-0.14

POSITIVE LOGITS

orton

0.17

inery

0.16

esters

0.15

loff

0.15

0.14

Ãµi

0.14

à¸ł

0.14

Activations Density 0.242%

numerical data and statistics related to health and economics

No Comments

No Known Activations