INDEX

Explanations

references to "century" or related variations indicating time periods or anniversaries

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

oro

-0.17

eron

-0.15

erial

-0.14

iction

-0.14

anza

-0.14

icÃŃ

-0.14

ora

-0.14

ÐµÑĢÐ°

-0.14

ÑĢÐ°Ñĩ

-0.13

 entry

-0.13

POSITIVE LOGITS

eyn

0.17

ames

0.16

combe

0.15

well

0.15

illos

0.15

roids

0.15

imeters

0.15

avanaugh

0.15

bis

0.14

ovÃŃ

0.14

Activations Density 0.013%

references to "century" or related variations indicating time periods or anniversaries

No Comments

No Known Activations