INDEX

Explanations

characters or symbols used in specific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 toasted

-0.12

swagger

-0.12

urum

-0.12

iot

-0.12

longleftrightarrow

-0.11

_excel

-0.11

ikon

-0.11

andro

-0.11

 Gale

-0.11

 sandwiches

-0.11

POSITIVE LOGITS

 Player

0.27

 Scene

0.25

 scene

0.25

 Nodes

0.24

 Node

0.24

 player

0.23

Player

0.23

Scene

0.22

Node

0.22

 Scenes

0.22

Activations Density 0.004%

characters or symbols used in specific contexts

No Comments

No Known Activations