INDEX

Explanations

references to seminars or educational events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ill

-0.16

 Moor

-0.16

OTA

-0.16

zip

-0.15

Ill

-0.15

iaux

-0.15

otropic

-0.15

 Fury

-0.15

ASN

-0.14

.spatial

-0.14

POSITIVE LOGITS

exp

0.20

 foreigners

0.19

ucher

0.15

 fashion

0.14

 cement

0.14

ÏĥÏĨ

0.14

 Cement

0.14

 Asia

0.14

herits

0.14

(IDC

0.13

Activations Density 0.473%

references to seminars or educational events

No Comments

No Known Activations