INDEX

Explanations

locations or proper nouns referring to towns or cities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

upertino

-0.16

eba

-0.15

ELLOW

-0.15

ÑĥÑĢÐ³

-0.15

outu

-0.15

ABCDEFGHIJKLMNOP

-0.14

.mutable

-0.14

anson

-0.14

\grid

-0.14

mul

-0.14

POSITIVE LOGITS

hoa

0.16

antro

0.14

cies

0.14

 Fisher

0.14

adoras

0.14

JsonValue

0.14

bens

0.14

FDA

0.14

ades

0.14

ados

0.14

Activations Density 0.010%

locations or proper nouns referring to towns or cities

No Comments

No Known Activations