INDEX

Explanations

specific identifiers and labels related to locations and systems in a transport or facility context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

éļ

-0.15

Fall

-0.14

ãģĨãģ¡

-0.14

ebe

-0.14

asje

-0.14

dns

-0.14

dz

-0.14

emory

-0.14

otch

-0.14

kiego

-0.13

POSITIVE LOGITS

meer

0.15

DMI

0.15

stre

0.15

.gb

0.14

adem

0.14

é¤¨

0.14

éĤ

0.14

cen

0.14

ATAB

0.14

Activations Density 0.265%

specific identifiers and labels related to locations and systems in a transport or facility context

No Comments

No Known Activations