INDEX

Explanations

references to legal proceedings and penalties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

isel

-0.15

 overhead

-0.15

aptive

-0.14

CV

-0.14

.resolution

-0.14

 Resolution

-0.14

çĬ

-0.13

.CV

-0.13

 hobby

-0.13

Resolution

-0.13

POSITIVE LOGITS

 Sessions

0.25

FIR

0.24

Sessions

0.23

IPC

0.21

IPC

0.20

ooks

0.20

 sessions

0.20

 cogn

0.20

sessions

0.19

 chall

0.19

Activations Density 0.052%

references to legal proceedings and penalties

No Comments

No Known Activations