INDEX

Explanations

phrases indicating extension or expansion of ideas or initiatives

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

AMI

-0.16

icap

-0.15

Ð¾Ð±Ð¸

-0.15

ÑĢÐ°Ð¿

-0.15

 Succ

-0.15

ondo

-0.14

.returnValue

-0.14

stalk

-0.14

ipline

-0.14

rts

-0.14

POSITIVE LOGITS

vert

0.18

.xhtml

0.16

 "(\<

0.15

ï¿

0.15

PRINTF

0.15

ÅĤy

0.15

ode

0.15

è§ī

0.14

inous

0.14

heit

0.14

Activations Density 0.047%

phrases indicating extension or expansion of ideas or initiatives

No Comments

No Known Activations