INDEX

Explanations

prepositions indicating suitability or adequacy for specific conditions or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

aire

-0.15

°

-0.15

aret

-0.15

èªł

-0.15

ardy

-0.14

 Vacation

-0.14

alous

-0.14

 vacation

-0.13

 convex

-0.13

hea

-0.13

POSITIVE LOGITS

enze

0.16

fer

0.16

 Ribbon

0.15

ÐµÑĢÐ±

0.14

ozor

0.14

-syntax

0.14

mn

0.14

fm

0.14

ë¶

0.13

rote

0.13

Activations Density 0.021%

prepositions indicating suitability or adequacy for specific conditions or subjects

No Comments

No Known Activations