INDEX

Explanations

historical references and events related to significant figures and moments in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 supply

-0.15

 Supply

-0.15

ÏĢÎŃ

-0.15

apur

-0.15

ÂŁ

-0.14

pek

-0.14

acades

-0.14

supply

-0.14

.Modified

-0.14

êµ¬

-0.14

POSITIVE LOGITS

amps

0.16

sos

0.15

mos

0.14

amping

0.14

rex

0.13

fax

0.13

 lingering

0.13

ifax

0.13

 Tiny

0.13

ander

0.13

Activations Density 0.587%

historical references and events related to significant figures and moments in various contexts

No Comments

No Known Activations