INDEX

Explanations

prepositions and their contextual use in various phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

zeÅĦ

-0.15

kowski

-0.15

 conex

-0.14

.createFrom

-0.14

ÅĤaw

-0.14

[arg

-0.13

Äĥng

-0.13

sek

-0.13

 connexion

-0.13

itin

-0.13

POSITIVE LOGITS

-to

0.15

erta

0.15

prav

0.14

 Prosper

0.14

áº¤

0.14

iets

0.13

áº¡

0.13

ãĥ©ãĥĥãĤ¯

0.13

 puck

0.13

_boost

0.13

Activations Density 0.035%

prepositions and their contextual use in various phrases

No Comments

No Known Activations