INDEX

Explanations

concepts related to operational processes and metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Ã¤l

-0.15

duino

-0.15

antity

-0.14

ãĥĪãĥª

-0.14

tracer

-0.14

 lover

-0.14

mina

-0.14

blas

-0.14

ickey

-0.13

udic

-0.13

POSITIVE LOGITS

gle

0.15

isper

0.15

 Across

0.15

Across

0.14

aken

0.14

ergarten

0.13

 across

0.13

 irre

0.13

.nr

0.13

Activations Density 0.164%

concepts related to operational processes and metrics

No Comments

No Known Activations