INDEX

Explanations

details about specific locations and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ã¼ns

-0.18

 Ontario

-0.16

 Ballard

-0.16

bote

-0.16

Ont

-0.15

Ont

-0.14

ilig

-0.14

Ð´Ð°Ð½

-0.14

hydr

-0.14

 SHARE

-0.14

POSITIVE LOGITS

ixin

0.17

osi

0.16

ods

0.15

arel

0.15

ias

0.15

arkin

0.14

idas

0.14

à¹ĥà¸Ī

0.14

fur

0.14

 Princip

0.14

Activations Density 0.093%

details about specific locations and their characteristics

No Comments

No Known Activations