INDEX

Explanations

references to merging data and strategies for data integration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

isl

-0.16

 reserves

-0.15

ray

-0.15

rot

-0.15

eid

-0.15

 reserve

-0.14

rot

-0.14

 reserv

-0.14

arg

-0.14

rev

-0.14

POSITIVE LOGITS

ault

0.17

-sama

0.17

kir

0.16

emes

0.15

adow

0.15

hausen

0.15

esk

0.14

tape

0.14

tures

0.14

cken

0.14

Activations Density 0.017%

references to merging data and strategies for data integration

No Comments

No Known Activations