INDEX

Explanations

references to the pronoun "it."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

_utilities

-0.15

mont

-0.14

adas

-0.14

 olsun

-0.14

ê³¡

-0.14

 sebou

-0.14

ause

-0.14

tolua

-0.14

Ð´Ð¸Ð½Ð°

-0.14

POSITIVE LOGITS

iner

0.42

chy

0.32

ching

0.26

unes

0.26

alo

0.23

ches

0.23

alic

0.23

inerary

0.23

aly

0.22

 raining

0.21

Activations Density 0.540%

references to the pronoun "it."

No Comments

No Known Activations