INDEX

Explanations

date references and specific terms associated with events or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

kinson

-0.19

fully

-0.19

incinn

-0.15

Ø§Ø¡

-0.15

ÄįnÃŃk

-0.14

riel

-0.14

_PRI

-0.14

Ø¦Ø©

-0.14

ichel

-0.14

artin

-0.14

POSITIVE LOGITS

ä»½

0.19

nard

0.18

hem

0.17

ÑģÐ¾ÑĤ

0.16

iÃ¨me

0.16

ilateral

0.15

 weather

0.15

embers

0.15

ãĥ³ãĥĳ

0.15

Ä±s

0.15

Activations Density 0.096%

date references and specific terms associated with events or milestones

No Comments

No Known Activations