INDEX

Explanations

specific institutional and administrative terms, particularly in education and labor contexts

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

erus

-0.18

 span

-0.16

esan

-0.15

OP

-0.15

Ruf

-0.14

 Great

-0.14

hek

-0.14

 prec

-0.14

Alv

-0.14

mj

-0.14

POSITIVE LOGITS

orris

0.15

 punishable

0.15

 ########.

0.14

onec

0.14

nosis

0.14

kinci

0.14

Ä±nd

0.14

ovich

0.14

Activations Density 0.007%

specific institutional and administrative terms, particularly in education and labor contexts

No Comments

No Known Activations