INDEX

Explanations

references to historical or cultural locations and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

_NT

-0.17

obao

-0.16

egan

-0.15

chine

-0.15

 unbiased

-0.14

ileo

-0.14

uil

-0.14

.SIG

-0.14

onia

-0.14

ilyn

-0.14

POSITIVE LOGITS

.define

0.16

ÑĢÐ°Ð²Ð¸

0.15

ajs

0.14

ifice

0.14

orra

0.14

 Paras

0.13

 Microsystems

0.13

 ÑģÐ²ÐµÑĤ

0.13

irus

0.13

ateria

0.13

Activations Density 0.420%

references to historical or cultural locations and activities

No Comments

No Known Activations