INDEX

Explanations

references to opportunities or positions available in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

erti

-0.17

icens

-0.17

oga

-0.16

zcze

-0.15

coli

-0.15

erli

-0.15

æ±Ĺ

-0.15

bben

-0.14

iez

-0.14

umbo

-0.14

POSITIVE LOGITS

pire

0.16

0.15

Ã±os

0.14

aversal

0.14

art

0.14

å¾Ĵ

0.14

piry

0.13

Proto

0.13

grim

0.13

Activations Density 0.113%

references to opportunities or positions available in various contexts

No Comments

No Known Activations