INDEX

Explanations

geographical locations and related services or features

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

afort

-0.15

etz

-0.14

_attached

-0.14

endor

-0.14

ogene

-0.13

quete

-0.13

 acqu

-0.13

ksi

-0.13

INGTON

-0.13

ysl

-0.13

POSITIVE LOGITS

 Gree

0.19

kest

0.16

ãĥ³ãĥģ

0.15

 ÐºÑĢÐ°Ð¹

0.14

opr

0.14

_truth

0.14

uling

0.14

Ð½Ð°Ñħ

0.14

Î³ÎºÎ±

0.14

elong

0.13

Activations Density 0.379%

geographical locations and related services or features

No Comments

No Known Activations