INDEX

Explanations

programming syntax and keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ossa

-0.16

 Reporter

-0.14

uhl

-0.14

okane

-0.14

 Filip

-0.14

çĽ®ãģ®

-0.14

 dissertation

-0.13

_LOADED

-0.13

_ValueChanged

-0.13

æı¡

-0.13

POSITIVE LOGITS

 syntax

0.37

 operator

0.37

 construct

0.35

 statement

0.34

 operators

0.31

è¯Ń

0.31

operator

0.30

 keyword

0.30

 command

0.29

 statements

0.28

Activations Density 0.127%

programming syntax and keywords

No Comments

No Known Activations