INDEX

Explanations

technical terms and code-related functions in 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ã£

-0.15

æŀ¶

-0.15

OX

-0.15

olvers

-0.15

 Freed

-0.14

Pay

-0.14

 accessory

-0.14

 Comey

-0.14

lement

-0.14

 Montgomery

-0.14

POSITIVE LOGITS

Ext

0.16

unan

0.16

Ext

0.16

_extend

0.16

$.

0.15

(function

0.15

 Backbone

0.15

ãİ

0.15

 fabric

0.15

//**↵

0.15

Activations Density 2.793%

technical terms and code-related functions in a programming context

No Comments

No Known Activations