INDEX

Explanations

structured programming elements, particularly related to class and method definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ammable

-0.16

iente

-0.15

 Long

-0.15

(*)

-0.15

âĢŀ

-0.15

 behavior

-0.14

Edited

-0.14

 Wass

-0.14

onom

-0.13

/uploads

-0.13

POSITIVE LOGITS

 public

0.20

#region

0.17

 string

0.17

 bool

0.17

public

0.16

erap

0.15

 readonly

0.15

	string

0.15

bool

0.15

	public

0.15

Activations Density 0.014%

structured programming elements, particularly related to class and method definitions

No Comments

No Known Activations