INDEX

Explanations

references to educational rankings and evaluations in media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orado

-0.15

onte

-0.15

berger

-0.15

ogo

-0.15

ë§ī

-0.14

ilk

-0.14

lÃ¡n

-0.13

ãģ°

-0.13

estroy

-0.13

 Nobel

-0.13

POSITIVE LOGITS

asco

0.16

alia

0.15

overrides

0.14

idor

0.14

klÃ¤

0.14

ÙĨÙĬÙĨ

0.14

BW

0.14

owers

0.13

 polls

0.13

 à¤ħà¤ĸ

0.13

Activations Density 0.029%

references to educational rankings and evaluations in media

No Comments

No Known Activations