INDEX

Explanations

references to sibling and next node relationships in hierarchical structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

beck

-0.17

hiba

-0.16

 migrationBuilder

-0.16

esome

-0.14

benh

-0.14

âĶģ

-0.14

izmet

-0.14

 buurt

-0.14

/dat

-0.13

POSITIVE LOGITS

-generation

0.15

Ã©

0.15

Tic

0.15

odont

0.15

[o

0.14

oin

0.14

Ð²Ð¸ÑĩÐ°Ð¹

0.14

Ð¸Ð»Ð¾

0.14

dde

0.14

 Raider

0.13

Activations Density 0.030%

references to sibling and next node relationships in hierarchical structures

No Comments

No Known Activations