INDEX

Explanations

instances of the word "Madison."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

éĳĳ

-0.17

frei

-0.17

.scalablytyped

-0.16

/Typography

-0.15

ilst

-0.15

evin

-0.15

eria

-0.14

igators

-0.14

ropol

-0.14

nbsp

-0.14

POSITIVE LOGITS

eline

0.22

leine

0.18

Mad

0.18

libs

0.17

mad

0.16

rig

0.16

mad

0.16

Mad

0.16

aller

0.16

onna

0.15

Activations Density 0.026%

instances of the word "Madison."

No Comments

No Known Activations