INDEX

Explanations

references to legislative actions or propositions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ering

-0.18

phy

-0.17

ane

-0.17

ered

-0.16

ãĤĥ

-0.16

er

-0.15

ritt

-0.15

rane

-0.14

rupt

-0.14

å¯Ĩ

-0.14

POSITIVE LOGITS

rieve

0.25

atri

0.23

lica

0.23

ulsive

0.22

 resent

0.22

uls

0.20

lication

0.20

rep

0.20

licate

0.20

udi

0.19

Activations Density 0.017%

references to legislative actions or propositions

No Comments

No Known Activations