INDEX

Explanations

specific place names or locations mentioned in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.14

OTO

-0.14

andas

-0.14

 Laden

-0.14

avana

-0.13

amarin

-0.13

ØºÙħ

-0.13

Ø§Ø¦Ø¹

-0.13

_Runtime

-0.13

amma

-0.13

POSITIVE LOGITS

iday

0.15

htmlspecialchars

0.14

issen

0.14

ois

0.14

onna

0.14

oise

0.14

CAC

0.14

perse

0.14

ibold

0.13

Activations Density 0.036%

specific place names or locations mentioned in the text

No Comments

No Known Activations