INDEX

Explanations

references to political primaries and candidates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ä¸ĺ

-0.17

ossa

-0.15

aÃ±

-0.15

ë§¥

-0.15

abei

-0.15

eker

-0.15

 Sabha

-0.14

 meis

-0.14

Å¥

-0.14

anas

-0.14

POSITIVE LOGITS

 Globe

0.15

ect

0.14

itioner

0.14

Glo

0.14

du

0.13

 Gott

0.13

 dÃ¡n

0.13

 Pols

0.13

Activations Density 0.047%

references to political primaries and candidates

No Comments

No Known Activations