INDEX

Explanations

phrases expressing various concepts of "about."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

HEMA

-0.15

 Specs

-0.15

quette

-0.14

å½

-0.14

Sle

-0.14

rove

-0.14

ycz

-0.13

imbus

-0.13

.GroupLayout

-0.13

alli

-0.13

POSITIVE LOGITS

dden

0.18

lhs

0.14

 neither

0.14

art

0.14

aida

0.14

rans

0.14

imei

0.13

akh

0.13

.vars

0.13

anza

0.13

Activations Density 0.030%

phrases expressing various concepts of "about."

No Comments

No Known Activations