INDEX

Explanations

words indicating multiplicity or multiple components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

nt

-0.16

##_

-0.16

IPS

-0.15

ered

-0.15

side

-0.15

si

-0.15

rig

-0.15

nc

-0.14

 abstract

-0.14

niest

-0.14

POSITIVE LOGITS

Äįer

0.15

uzey

0.15

qml

0.15

phis

0.15

uisse

0.14

.AutoComplete

0.14

antt

0.14

.XR

0.14

olk

0.14

inu

0.14

Activations Density 0.003%

words indicating multiplicity or multiple components

No Comments

No Known Activations