INDEX

Explanations

references to numerical statistics or measurements related to time, location, and demographic data

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

ework

-0.15

="<<

-0.15

_iterator

-0.15

mund

-0.14

elight

-0.14

ãĤ±ãĥĥãĥĪ

-0.14

hled

-0.14

à¸Ļà¸²à¸¡

-0.14

ehir

-0.14

SharedPtr

-0.13

POSITIVE LOGITS

olia

0.16

Mob

0.16

rÃ¡l

0.15

ference

0.15

onz

0.15

Ð°Ð»Ð¸Ð·Ð°ÑĨÐ¸Ð¸

0.15

ventions

0.15

western

0.14

enment

0.14

Activations Density 0.061%

references to numerical statistics or measurements related to time, location, and demographic data

No Comments

No Known Activations