INDEX

Explanations

mentions of "Google Reader" and related terms associated with digital feeds and services

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

èĤĥ

-0.16

izon

-0.15

icap

-0.15

 Hlav

-0.14

Ð¾Ð·Ð²

-0.14

ration

-0.13

amar

-0.13

ungi

-0.13

POSITIVE LOGITS

raith

0.16

 dying

0.15

bane

0.15

-era

0.15

BX

0.15

gone

0.15

è·¡

0.14

à¸¢à¸¡

0.14

forge

0.14

-Ray

0.14

Activations Density 0.369%

mentions of "Google Reader" and related terms associated with digital feeds and services

No Comments

No Known Activations