INDEX

Explanations

references to educational institutions and related locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

cem

-0.17

dings

-0.15

ÑģÐ»Ð¸

-0.14

ÐµÑĢÐ°ÑĤÑĥÑĢÐ°

-0.14

ieux

-0.14

ÐµÐ»ÐµÑĦ

-0.14

ndo

-0.14

keterangan

-0.14

onds

-0.14

Ã²i

-0.13

POSITIVE LOGITS

USA

0.15

 inters

0.14

con

0.14

prech

0.14

 choir

0.14

hh

0.14

urb

0.14

ongan

0.14

ondheim

0.13

Activations Density 0.208%

references to educational institutions and related locations

No Comments

No Known Activations