INDEX

Explanations

references to programming interfaces and attribution in technical documents

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

 Interracial

-0.15

ansa

-0.14

kins

-0.14

lection

-0.14

LIKELY

-0.14

keh

-0.14

aines

-0.13

apons

-0.13

verts

-0.13

noÅĽci

-0.13

POSITIVE LOGITS

Subsystem

0.15

OLUMNS

0.14

PCS

0.14

íĹĮ

0.13

amarin

0.13

çľ

0.13

aus

0.13

å¶

0.13

pcm

0.13

LLL

0.13

Activations Density 0.028%

references to programming interfaces and attribution in technical documents

No Comments

No Known Activations