INDEX

Explanations

references to diplomats and their titles, particularly ambassadors

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

apan

-0.16

ijo

-0.15

 Lamar

-0.15

Ð¸ÑĤÐ¾Ð¼

-0.15

 mobility

-0.14

 Rath

-0.14

TMP

-0.14

arp

-0.14

ondo

-0.13

 Sadd

-0.13

POSITIVE LOGITS

osate

0.17

olarity

0.15

eye

0.15

mux

0.15

vap

0.15

prav

0.14

[Index

0.14

Fog

0.14

ÏĢÎ¿ÏĤ

0.14

Ø´ÛĮ

0.14

Activations Density 0.044%

references to diplomats and their titles, particularly ambassadors

No Comments

No Known Activations