INDEX

Explanations

code elements 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 bool

-0.20

(bool

-0.19

bool

-0.17

 false

-0.17

int

-0.17

(boolean

-0.17

 string

-0.17

int

-0.16

false

-0.16

	bool

-0.16

POSITIVE LOGITS

 protected

0.17

 public

0.16

.prot

0.15

%[

0.14

 restricted

0.14

 confined

0.14

@SuppressWarnings

0.14

Unchecked

0.14

.optional

0.13

 giÃ¡o

0.13

Activations Density 0.032%

code elements related to class and method definitions

No Comments

No Known Activations