INDEX

Explanations

references to historical events and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

heim

-0.17

 antid

-0.17

zÃ¡

-0.16

GIN

-0.15

 Bang

-0.15

reen

-0.15

Ey

-0.15

Äįan

-0.14

isy

-0.14

atters

-0.14

POSITIVE LOGITS

elsen

0.17

bote

0.16

esp

0.15

 æ¥

0.15

.INTERNAL

0.15

 Cust

0.14

elper

0.14

ptic

0.14

ning

0.14

andler

0.14

Activations Density 0.083%

references to historical events and figures

No Comments

No Known Activations