INDEX

Explanations

phrases related to meeting standards or requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

erte

-0.17

ki

-0.15

hound

-0.14

ä¼

-0.14

atti

-0.13

 Burnett

-0.13

KI

-0.13

ation

-0.13

Î¿Î»

-0.13

POSITIVE LOGITS

 expectations

0.15

artner

0.15

tle

0.15

 standards

0.15

illance

0.15

expect

0.15

ropolis

0.14

chl

0.14

ters

0.14

renderer

0.14

Activations Density 0.045%

phrases related to meeting standards or requirements

No Comments

No Known Activations