INDEX

Explanations

references to measures or scores in evaluations or rankings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð»ÑıÐ²

-0.16

 Wagner

-0.15

 Cole

-0.15

Ã´le

-0.14

âĢ¦

-0.14

wd

-0.13

Ole

-0.13

 fasting

-0.13

Gh

-0.13

POSITIVE LOGITS

 Public

0.34

 PUBLIC

0.31

Public

0.30

ken

0.28

 public

0.26

/Public

0.25

.Public

0.25

_public

0.24

_PUBLIC

0.23

PUBLIC

0.23

Activations Density 0.001%

references to measures or scores in evaluations or rankings

No Comments

No Known Activations