INDEX

Explanations

references to legislative actions and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 tens

-0.14

ÃĹ↵↵

-0.13

 demanded

-0.13

Accent

-0.13

atak

-0.13

 Ð¿ÑĢÐ°Ð²Ð´Ð°

-0.13

Ã¡ct

-0.13

readcr

-0.13

&m

-0.13

è¦ª

-0.13

POSITIVE LOGITS

 motion

0.23

-motion

0.22

Motion

0.21

motion

0.20

 discussion

0.20

 Motion

0.20

OTION

0.17

 ì§Ī

0.17

 discussed

0.16

 discuss

0.16

Activations Density 0.034%

references to legislative actions and decisions

No Comments

No Known Activations