INDEX

Explanations

phrases or words indicating causation or consequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

pai

-0.15

rani

-0.14

 FITNESS

-0.14

VERBOSE

-0.13

à¸¢à¸§

-0.13

æīķ

-0.13

ovan

-0.13

Wir

-0.13

uters

-0.13

SWG

-0.13

POSITIVE LOGITS

iloc

0.16

Sas

0.16

rame

0.15

æĴ

0.15

ord

0.15

ook

0.15

inder

0.14

ldb

0.14

avid

0.14

.dimension

0.14

Activations Density 0.089%

phrases or words indicating causation or consequence

No Comments

No Known Activations