INDEX

Explanations

names of specific geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ayet

-0.17

arry

-0.15

cher

-0.15

atron

-0.15

odega

-0.14

agic

-0.14

Subsystem

-0.14

ActionButton

-0.13

ĤŃ

-0.13

adio

-0.13

POSITIVE LOGITS

orer

0.15

 Rosenstein

0.15

ilig

0.15

upa

0.14

.cg

0.14

istent

0.13

å®Ļ

0.13

shire

0.13

erve

0.13

_cmos

0.13

Activations Density 0.058%

names of specific geographical locations

No Comments

No Known Activations