INDEX

Explanations

references to international military and political involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

å¥ĳ

-0.16

OTE

-0.16

azzi

-0.16

makt

-0.16

OVE

-0.15

æ·

-0.15

ãĥ¼ãĤ¸

-0.15

èĸ

-0.14

ivor

-0.14

ventus

-0.14

POSITIVE LOGITS

 recip

0.21

 itself

0.19

 station

0.19

isch

0.17

 dispatch

0.17

 flex

0.17

ob

0.17

 Barnett

0.17

 engaged

0.16

 exports

0.16

Activations Density 0.148%

references to international military and political involvement

No Comments

No Known Activations