INDEX

Explanations

programming-related terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

//{{

-0.16

_tC

-0.16

thouse

-0.15

atatype

-0.15

/******/

-0.15

ennon

-0.15

 Coll

-0.14

oose

-0.14

_guess

-0.14

dol

-0.14

POSITIVE LOGITS

 negative

0.28

 Negative

0.24

 positive

0.24

negative

0.23

Negative

0.22

 Positive

0.22

=-

0.21

-negative

0.20

(-

0.20

positive

0.19

Activations Density 0.242%

programming-related terms and concepts

No Comments

No Known Activations