INDEX

Explanations

references to geographical or cultural entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ë¹ĦìĬ¤

-0.16

Fro

-0.16

ibs

-0.15

.useState

-0.15

errs

-0.14

Rt

-0.14

kes

-0.14

rie

-0.14

ihn

-0.14

onne

-0.14

POSITIVE LOGITS

 related

0.17

ide

0.17

Related

0.16

related

0.16

gni

0.15

 other

0.14

 https

0.14

IDE

0.13

https

0.13

UTC

0.13

Activations Density 0.005%

references to geographical or cultural entities

No Comments

No Known Activations