INDEX

Explanations

references to locations, particularly cities, and attributes related to costs and fees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

à¥įà¤¤à¤ķ

-0.17

imd

-0.17

bots

-0.16

avors

-0.14

JR

-0.14

joy

-0.14

IRR

-0.13

otic

-0.13

_OPTS

-0.13

ToJson

-0.13

POSITIVE LOGITS

&o

0.14

seau

0.14

Ø§Ø±Ùģ

0.14

à¤¾à¤Ĺà¤¤

0.14

AFX

0.14

_digest

0.14

oram

0.14

 Fletcher

0.13

 level

0.13

 filling

0.13

Activations Density 0.082%

references to locations, particularly cities, and attributes related to costs and fees

No Comments

No Known Activations