INDEX

Explanations

terms and concepts related to stochastic processes and Markovian properties

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

romium

-0.15

atten

-0.15

legg

-0.14

ecast

-0.14

typed

-0.14

TexCoord

-0.13

asco

-0.13

Ð°Ð½Ð¾

-0.13

asin

-0.13

xaa

-0.13

POSITIVE LOGITS

uni

0.15

rets

0.14

oad

0.14

Ä°n

0.14

 Storm

0.14

ngr

0.14

lew

0.14

 Trailer

0.14

 IDENT

0.14

.ident

0.14

Activations Density 0.637%

terms and concepts related to stochastic processes and Markovian properties

No Comments

No Known Activations