INDEX

Explanations

references to government actions and societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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»ĭ

-0.15

-Regular

-0.13

OOT

-0.13

conciliation

-0.13

achuset

-0.13

leted

-0.13

erdem

-0.12

 ÑĥÐ´Ð°ÑĢ

-0.12

lient

-0.12

(:,:,

-0.12

POSITIVE LOGITS

‘

0.19

0.15

Ĥæķ°

0.15

chant

0.14

 judge

0.14

amu

0.14

 chant

0.14

byt

0.14

 glove

0.14

 latest

0.13

Activations Density 0.200%

references to government actions and societal issues

No Comments

No Known Activations