INDEX

Explanations

geographic locations or places 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

opsy

-0.19

ka

-0.18

 Kund

-0.14

Ã¦r

-0.14

ãĥ¥

-0.14

Ð¹Ð¾Ð¼

-0.14

unami

-0.14

Ð¾Ð¼

-0.14

ODB

-0.14

iev

-0.14

POSITIVE LOGITS

ãĥ¼ãĥ³

0.16

uppe

0.16

gis

0.16

 Buna

0.15

Ð°Ð½ÑĮ

0.15

pun

0.14

incip

0.14

valuator

0.14

 guilt

0.14

ann

0.14

Activations Density 0.004%

geographic locations or places mentioned in the text

No Comments

No Known Activations