INDEX

Explanations

references to specific legislative resolutions and bills

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

(;;

-0.15

Ã©ment

-0.15

ANNEL

-0.15

texts

-0.15

 Tray

-0.14

iks

-0.14

ãĥ¼ãĥ³

-0.14

wizard

-0.14

ÙĬØ§Øª

-0.14

rawler

-0.14

POSITIVE LOGITS

ault

0.16

 Paige

0.15

ispers

0.15

aco

0.14

autop

0.14

elden

0.14

 folds

0.14

 Happiness

0.14

eig

0.14

Activations Density 0.006%

references to specific legislative resolutions and bills

No Comments

No Known Activations