INDEX

Explanations

references to returning or coming back

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

oun

-0.17

Ð¾ÑĤÑĥ

-0.16

arten

-0.16

osh

-0.15

arms

-0.15

utin

-0.15

.ConnectionString

-0.15

oose

-0.14

fur

-0.14

arme

-0.14

POSITIVE LOGITS

ProgressHUD

0.16

edException

0.14

 trace

0.14

legg

0.14

Ler

0.14

quist

0.14

ckett

0.14

 traced

0.13

dl

0.13

Activations Density 0.040%

references to returning or coming back

No Comments

No Known Activations