INDEX

Explanations

code-related elements and structures within a programming context

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

 Gauge

-0.15

 Gott

-0.14

 Grove

-0.14

 Graz

-0.13

Gut

-0.13

 Wolf

-0.13

eph

-0.12

à¹ĩà¸Ķ

-0.12

Ses

-0.12

Gay

-0.12

POSITIVE LOGITS

 generation

0.98

 Generation

0.91

 GENER

0.87

 generator

0.83

-generation

0.82

 Gener

0.82

 generators

0.82

Generation

0.82

 generating

0.81

generation

0.81

Activations Density 0.311%

code-related elements and structures within a programming context

No Comments

No Known Activations