INDEX

Explanations

phrases indicating geographic locations or institutional affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 McCart

-0.16

jvu

-0.16

ç«

-0.16

swire

-0.16

.EventArgs

-0.15

oppers

-0.14

Ð¾Ð¸ÑĤ

-0.14

arf

-0.14

reur

-0.14

abin

-0.14

POSITIVE LOGITS

Bay

0.15

-Smith

0.14

-base

0.14

 encore

0.14

Sor

0.14

ItemCount

0.14

WithName

0.13

 hardware

0.13

Activations Density 0.035%

phrases indicating geographic locations or institutional affiliations

No Comments

No Known Activations