INDEX

Explanations

punctuation marks and words related to formal documentation or scripts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

abase

-0.16

eryl

-0.15

istes

-0.14

 dens

-0.14

Tube

-0.14

ovat

-0.14

icit

-0.14

inq

-0.14

ìĬ¹

-0.14

 volum

-0.14

POSITIVE LOGITS

astes

0.16

ROC

0.15

eka

0.15

ninger

0.14

_GRE

0.14

inous

0.14

 Gordon

0.14

-bre

0.13

asted

0.13

å±

0.13

Activations Density 0.000%

punctuation marks and words related to formal documentation or scripts

No Comments

No Known Activations