INDEX

Explanations

references to government actions and official statements related to international relations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

á»Ńa

-0.16

 Monk

-0.14

.documentation

-0.14

 Robinson

-0.14

stead

-0.13

 ëª

-0.13

.mount

-0.13

Ð¾ÑĤÑĮ

-0.13

Discuss

-0.13

 Mont

-0.13

POSITIVE LOGITS

 pole

0.19

iron

0.19

 iron

0.19

 point

0.17

ronic

0.16

 repro

0.16

unga

0.16

 ironically

0.16

eva

0.15

dw

0.15

Activations Density 0.205%

references to government actions and official statements related to international relations

No Comments

No Known Activations