INDEX

Explanations

references to political figures and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ernaut

-0.17

.Invariant

-0.15

Unchecked

-0.15

pto

-0.14

dar

-0.14

umper

-0.14

Ð´Ð°Ð²

-0.14

asher

-0.14

fte

-0.14

åŁŁ

-0.14

POSITIVE LOGITS

 vote

0.40

 motion

0.40

 motions

0.37

 votes

0.35

 Motion

0.33

motion

0.32

Motion

0.31

 roll

0.30

 floor

0.29

 Vote

0.28

Activations Density 0.086%

references to political figures and their actions

No Comments

No Known Activations