INDEX

Explanations

military terms and associated organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

egr

-0.15

çĸĳ

-0.14

ENSE

-0.14

arella

-0.14

_DECLARE

-0.14

urs

-0.14

ours

-0.14

WX

-0.14

à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ

-0.14

roke

-0.14

POSITIVE LOGITS

acemark

0.16

portion

0.16

ÅĽ

0.15

 isize

0.15

ANA

0.15

)ìĿ´

0.14

£¨

0.14

 portion

0.14

èª

0.14

ÏĮÎ´

0.14

Activations Density 0.254%

military terms and associated organizations

No Comments

No Known Activations