INDEX

Explanations

references to educational materials and resources

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inki

-0.15

Å¯Å¾

-0.15

antino

-0.15

usk

-0.15

ux

-0.14

ationToken

-0.14

activex

-0.14

exampleInput

-0.14

[url

-0.13

 Kushner

-0.13

POSITIVE LOGITS

lege

0.16

erek

0.15

AREST

0.15

ãĥ¬ãĥ¼

0.15

ÑĥÑĢÑĥ

0.14

 Desc

0.14

Mine

0.14

Ã³z

0.14

 Crop

0.14

id

0.14

Activations Density 0.052%

references to educational materials and resources

No Comments

No Known Activations