INDEX

Explanations

mentions of Barack Obama

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

åłĤ

-0.14

ìħ

-0.14

cie

-0.14

wen

-0.14

fout

-0.14

vant

-0.13

uent

-0.13

osterone

-0.13

çĪ½

-0.13

POSITIVE LOGITS

ipa

0.16

InnerText

0.15

Ã©nÃ©

0.15

jom

0.15

izont

0.14

ÎłÏģÎ¿

0.14

 variant

0.14

chwitz

0.14

 Cycl

0.14

zÃŃ

0.14

Activations Density 0.013%

mentions of Barack Obama

No Comments

No Known Activations