INDEX

Explanations

references to Donald Trump and his administration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

cing

-0.15

ãģ¾ãģ¾

-0.15

oomla

-0.14

ÑıÐ¼

-0.14

 Stamford

-0.14

ÏģÎ¿Ïħ

-0.14

ãģĵãĤĵãģ«

-0.14

onn

-0.14

.cloudflare

-0.13

POSITIVE LOGITS

Nat

0.15

filer

0.15

linger

0.15

/bower

0.14

 amore

0.14

Ð³Ð»Ñı

0.14

CHED

0.14

 Ð¾Ð±ÑĢÐ°

0.14

 numeral

0.14

wid

0.13

Activations Density 0.031%

references to Donald Trump and his administration

No Comments

No Known Activations