INDEX

Explanations

references to programming elements, specifically nodes and JavaScript files

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

tright

-0.17

ner

-0.17

½æķ°

-0.16

-minded

-0.16

ships

-0.16

liÄŁine

-0.15

loaded

-0.15

ming

-0.15

nga

-0.15

loe

-0.15

POSITIVE LOGITS

fault

0.20

_modules

0.20

hood

0.20

ules

0.18

FAULT

0.17

lets

0.17

hole

0.16

lete

0.16

id

0.15

owner

0.15

Activations Density 0.079%

references to programming elements, specifically nodes and JavaScript files

No Comments

No Known Activations