INDEX

Explanations

references to code structure or software components 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 @ 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

aghan

-0.17

avadoc

-0.14

igne

-0.14

yi

-0.14

inge

-0.14

icho

-0.14

uron

-0.14

agan

-0.14

Whe

-0.13

pur

-0.13

POSITIVE LOGITS

ÐĲÑĢÑħÑĸÐ²

0.17

âĦĸâĦĸ

0.16

ugins

0.15

>NN

0.15

MAIN

0.15

modelo

0.15

ValueCollection

0.14

main

0.14

.googlecode

0.14

Activations Density 0.039%

references to code structure or software components within a programming context

No Comments

No Known Activations