INDEX

Explanations

references to dates and measurements in a temporal or measurement context

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

pone

-0.17

ETERS

-0.15

holm

-0.15

etro

-0.14

æī¬

-0.14

etry

-0.14

gars

-0.14

 pozor

-0.13

onso

-0.13

etri

-0.13

POSITIVE LOGITS

ÑĩÐµ

0.14

nds

0.14

arro

0.14

ÑıÐ¶

0.14

 pudd

0.14

plib

0.14

omy

0.14

folk

0.13

Ã¤

0.13

 ioctl

0.13

Activations Density 0.170%

references to dates and measurements in a temporal or measurement context

No Comments

No Known Activations