INDEX

Explanations

specific terms related to future expectations or projections

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

imb

-0.17

Hod

-0.16

 dispens

-0.15

 Hawth

-0.15

stell

-0.14

ager

-0.14

hora

-0.13

 Mare

-0.13

errat

-0.13

unker

-0.13

POSITIVE LOGITS

ÐµÐ³Ð¾ÑĢ

0.18

à¹ĥ

0.17

aper

0.16

etti

0.16

-tm

0.15

aman

0.15

richt

0.15

otal

0.14

eneric

0.14

raÅ¾

0.14

Activations Density 0.000%

specific terms related to future expectations or projections

No Comments

No Known Activations