INDEX

Explanations

references to notable individuals or researchers in academic contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

vale

-0.14

inode

-0.14

bage

-0.14

icrous

-0.14

piler

-0.14

-LAST

-0.13

Ð½Ð¸ÐºÐµ

-0.13

uars

-0.13

ippy

-0.13

.scalablytyped

-0.13

POSITIVE LOGITS

icious

0.14

Zuk

0.14

imson

0.14

 destino

0.13

kÄ±

0.13

_CAST

0.13

Hut

0.13

crease

0.12

 stranger

0.12

istor

0.12

Activations Density 0.457%

references to notable individuals or researchers in academic contexts

No Known Activations