INDEX

Explanations

punctuation marks and non-standard text elements

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

iero

-0.15

iano

-0.15

notation

-0.15

 tender

-0.15

 rady

-0.14

vio

-0.14

 tent

-0.14

les

-0.14

kke

-0.14

POSITIVE LOGITS

urette

0.16

ÑĥÑĢÐ¸

0.16

uft

0.16

_frm

0.15

Äįas

0.14

æĺĵ

0.14

.cx

0.14

owski

0.14

FRING

0.14

Activations Density 0.211%

punctuation marks and non-standard text elements

No Comments

No Known Activations