INDEX

Explanations

negations or terms indicating lack or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

brain

-0.16

moz

-0.15

ullet

-0.15

 brain

-0.15

jerne

-0.14

 trans

-0.14

 Brain

-0.14

 brains

-0.14

uide

-0.14

POSITIVE LOGITS

bsolute

0.16

laÄį

0.15

ë¡Ŀ

0.14

inia

0.14

ifa

0.14

 kles

0.14

GBK

0.14

observer

0.14

lue

0.14

Activations Density 0.000%

negations or terms indicating lack or absence

No Comments

No Known Activations