INDEX

Explanations

references to awards and recognition programs

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

inde

-0.16

AILS

-0.15

ifu

-0.14

esan

-0.14

 inde

-0.14

ords

-0.14

 Initi

-0.14

 nackte

-0.14

udas

-0.13

ivers

-0.13

POSITIVE LOGITS

 criteria

0.23

criteria

0.23

 Criteria

0.21

Criteria

0.20

Deadline

0.20

 criterion

0.19

riteria

0.19

 DEAD

0.19

deadline

0.19

 submissions

0.18

Activations Density 0.095%

references to awards and recognition programs

No Comments

No Known Activations