INDEX

Explanations

references to communication and relationships 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

zs

-0.15

IOC

-0.13

utr

-0.13

emet

-0.13

enn

-0.13

hoff

-0.13

OWN

-0.13

ula

-0.13

acher

-0.13

.LayoutStyle

-0.13

POSITIVE LOGITS

.scalajs

0.14

fos

0.14

ugins

0.13

lossen

0.13

æ±º

0.13

Ð»Ñı

0.13

allas

0.13

è¨º

0.13

FTA

0.13

 cogn

0.13

Activations Density 0.999%

references to communication and relationships in various contexts

No Comments

No Known Activations