INDEX

Explanations

phrases that indicate abundance or a large number of items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

sworth

-0.17

ÑĮÑı

-0.17

anz

-0.16

oeff

-0.15

cas

-0.14

oved

-0.14

piece

-0.14

stash

-0.14

asthan

-0.13

otec

-0.13

POSITIVE LOGITS

 plenty

0.15

 enough

0.15

forme

0.15

erre

0.15

eva

0.14

vy

0.14

 supply

0.14

enty

0.14

eny

0.13

 Plenty

0.13

Activations Density 0.014%

phrases that indicate abundance or a large number of items

No Comments

No Known Activations