INDEX

Explanations

mathematical expressions and equations

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

cce

-0.16

AR

-0.15

erver

-0.14

andro

-0.14

sta

-0.14

rais

-0.14

esan

-0.14

mus

-0.14

unta

-0.14

æĲŃ

-0.14

POSITIVE LOGITS

uling

0.18

ddy

0.16

Ð»Ð°Ð´Ð°

0.14

ãĥ©ãĤ¤ãĥ³

0.14

 Neon

0.14

=target

0.14

ãģĹãģ¦ãĤĤ

0.14

ampus

0.13

ãĥį

0.13

æīķ

0.13

Activations Density 0.044%

mathematical expressions and equations

No Comments

No Known Activations