INDEX

Explanations

relationships among family members

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ej

-0.16

amins

-0.15

esor

-0.14

bruar

-0.14

éĲĺ

-0.14

addAction

-0.14

eba

-0.14

bew

-0.13

inne

-0.13

 jspb

-0.13

POSITIVE LOGITS

è£Ŀ

0.16

ALLY

0.15

enty

0.15

agen

0.14

 Extras

0.14

avel

0.14

 chron

0.13

 dich

0.13

è£ħ

0.13

aler

0.13

Activations Density 0.005%

relationships among family members

No Comments

No Known Activations