INDEX

Explanations

mentions of groups or classes of people, particularly in a reunion context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Ã¡bado

-0.15

lige

-0.15

ì£

-0.14

eros

-0.14

izioni

-0.14

 Chron

-0.14

creds

-0.14

à¸²à¸¨

-0.14

regunta

-0.14

viar

-0.13

POSITIVE LOGITS

 batch

0.21

ux

0.19

batch

0.19

 Batch

0.17

 batches

0.16

 cohort

0.15

 BATCH

0.15

.batch

0.15

Batch

0.15

Duy

0.15

Activations Density 0.079%

mentions of groups or classes of people, particularly in a reunion context

No Comments

No Known Activations